Tag Archives: ICLR

Google at ICLR 2020



This week marks the beginning of the 8th International Conference on Learning Representations (ICLR 2020), a fully virtual conference focused on how one can learn meaningful and useful representations of data for machine learning. ICLR offers conference and workshop tracks, both of which include invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction and issues regarding non-convex optimization.

As a Diamond Sponsor of ICLR 2020, Google will have a strong virtual presence with over 80 publications accepted, in addition to participating on organizing committees and in workshops. If you have registered for ICLR 20202, we hope you'll watch our talks and learn about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at ICLR 2020 in the list below (Googlers highlighted in blue).

Officers and Board Members
Includes: Hugo LaRochelle, Samy Bengio, Tara Sainath

Organizing Committee
Includes: Kevin Swersky, Timnit Gebru

Area Chairs
Includes: Balaji Lakshminarayanan, Been Kim, Chelsea Finn, Dale Schuurmans, George Tucker, Honglak Lee, Hossein Mobahi, Jasper Snoek, Justin Gilmer, Katherine Heller, Manaal Faruqui, Michael Ryoo, Nicolas Le Roux, Sanmi Koyejo, Sergey Levine, Tara Sainath, Yann Dauphin, Anders Søgaard, David Duvenaud, Jamie Morgenstern, Qiang Liu

Publications
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference (see the blog post)
Lasse Espeholt, Raphaël Marinier, Piotr Stanczyk, Ke Wang, Marcin Michalski‎

Differentiable Reasoning Over a Virtual Knowledge Base
Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen

Dynamics-Aware Unsupervised Discovery of Skills
Archit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar, Karol Hausman

GenDICE: Generalized Offline Estimation of Stationary Values
Ruiyi Zhang, Bo Dai, Lihong Li, Dale Schuurmans

Mathematical Reasoning in Latent Space
Dennis Lee, Christian Szegedy, Markus N. Rabe, Kshitij Bansal, Sarah M. Loos

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
Will Grathwohl, Kuan-Chieh Wang, Jorn-Henrik Jacobsen, David Duvenaud, Kevin Swersky, Mohammad Norouzi

Adjustable Real-time Style Transfer
Mohammad Babaeizadeh, Golnaz Ghiasi

Are Transformers Universal Approximators of Sequence-to-sequence Functions?
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashankc J. Reddi, Sanjiv Kumar

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
Michael S. Ryoo, AJ Piergiovanni, Mingxing Tan, Anelia Angelova

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Dan Hendrycks, Norman Mu, Ekin D. Cubuk, Barret Zoph, Justin Gilmer, Balaji Lakshminarayanan

BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning
Yeming Wen, Dustin Tran, Jimmy Ba

Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning (see the blog post)
Ali Mousavi, Lihong Li, Qiang Liu, Dengyong Zhou

Can Gradient Clipping Mitigate Label Noise?
Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

CAQL: Continuous Action Q-Learning
Moonkyung Ryu, Yinlam Chow, Ross Anderson, Christian Tjandraatmadja, Craig Boutilier

Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
Byung Hoon Ahn, Prannoy Pilligundla, Amir Yazdanbakhsh, Hadi Esmaeilzadeh

Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization
Satrajit Chatterjee

Consistency Regularization for Generative Adversarial Networks
Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee

Contrastive Representation Distillation
Yonglong Tian, Dilip Krishnan, Phillip Isola

Deep Audio Priors Emerge from Harmonic Convolutional Networks
Zhoutong Zhang, Yunyun Wang, Chuang Gan, Jiajun Wu, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman

Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Yao Qin, Nicholas Frosst, Sara Sabour, Colin Raffel, Garrison Cottrell, Geoffrey Hinton

Detecting Extrapolation with Local Ensembles
David Madras, James Atwood, Alexander D'Amour

Disentangling Factors of Variations Using Few Labels
Francesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem

Distance-Based Learning from Errors for Confidence Calibration
Chen Xing, Sercan Ö. Arik, Zizhao Zhang, Tomas Pfister

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (see the blog post)
Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning

ES-MAML: Simple Hessian-Free Meta Learning (see the blog post)
Xingyou Song, Yuxiang Yang, Krzysztof Choromanski, Aldo Pacchiano, Wenbo Gao, Yunhao Tang

Exploration in Reinforcement Learning with Deep Covering Options
Yuu Jinnai, Jee Won Park, Marlos C. Machado, George Konidaris

Extreme Tensoring for Low-Memory Preconditioning
Xinyi Chen, Naman Agarwal, Elad Hazan, Cyril Zhang, Yi Zhang

Fantastic Generalization Measures and Where to Find Them
Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio

Generalization Bounds for Deep Convolutional Neural Networks
Philip M. Long, Hanie Sedghi

Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition
Jongbin Ryu, GiTaek Kwon, Ming-Hsuan Yang, Jongwoo Lim

Generative Models for Effective ML on Private, Decentralized Datasets
Sean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz, Mingqing Chen, Rajiv Mathews, Blaise Aguera y Arcas

Generative Ratio Matching Networks
Akash Srivastava, Kai Xu, Michael U. Gutmann, Charles Sutton

Global Relational Models of Source Code
Vincent J. Hellendoorn, Petros Maniatis, Rishabh Singh, Charles Sutton, David Bieber

Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
Suraj Nair, Chelsea Finn

Identity Crisis: Memorization and Generalization Under Extreme Overparameterization
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Michael C. Mozer, Yoram Singer

Imitation Learning via Off-Policy Distribution Matching
Ilya Kostrikov, Ofir Nachum, Jonathan Tompson

Language GANs Falling Short
Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joëlle Pineau, Laurent Charlin

Large Batch Optimization for Deep Learning: Training BERT in 76 Minutes
Yang You, Jing Li, Sashank Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, Cho-Jui Hsieh

Learning Execution through Neural Code Fusion
Zhan Shi, Kevin Swersky, Daniel Tarlow, Parthasarathy Ranganathan, Milad Hashemi

Learning Heuristics for Quantified Boolean Formulas through Reinforcement Learning
Gil Lederman, Markus N. Rabe, Edward A. Lee, Sanjit A. Seshia

Learning to Learn by Zeroth-Order Oracle
Yangjun Ruan, Yuanhao Xiong, Sashank Reddi, Sanjiv Kumar, Cho-Jui Hsieh

Learning to Represent Programs with Property Signatures
Augustus Odena, Charles Sutton

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
Runtian Zhai, Chen Dan, Di He, Huan Zhang, Boqing Gong, Pradeep Ravikumar, Cho-Jui Hsieh, Liwei Wang

Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
Daniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, Olivier Bousquet

Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
Sungryull Sohn, Hyunjae Woo, Jongwook Choi, Honglak Lee

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle

Model-based Reinforcement Learning for Biological Sequence Design
Christof Angermueller, David Dohan, David Belanger, Ramya Deshpande, Kevin Murphy, Lucy Colwell

Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
Kimin Lee, Kibok Lee, Jinwoo Shin, Honglak Lee

Observational Overfitting in Reinforcement Learning
Xingyou Song, Yiding Jiang, Stephen Tu, Behnam Neyshabur, Yilun Du

On Bonus-based Exploration Methods In The Arcade Learning Environment
Adrien Ali Taiga, William Fedus, Marlos C. Machado, Aaron Courville, Marc G. Bellemare

On Identifiability in Transformers
Gino Brunner, Yang Liu, Damian Pascual, Oliver Richter, Massimiliano Ciaramita, Roger Wattenhofer

On Mutual Information Maximization for Representation Learning
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic

On the Global Convergence of Training Deep Linear ResNets
Difan Zou, Philip M. Long, Quanquan Gu

Phase Transitions for the Information Bottleneck in Representation Learning
Tailin Wu, Ian Fischer

Pre-training Tasks for Embedding-based Large-scale Retrieval
Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, Sanjiv Kumar

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control
Nir Levine, Yinlam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh, Hung Bui

Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks
Wei Hu, Lechao Xiao, Jeffrey Pennington

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals

Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs
Aditya Paliwal, Felix Gimeno, Vinod Nair, Yujia Li, Miles Lubin, Pushmeet Kohli, Oriol Vinyals

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, Colin Raffel, Kihyuk Sohn

Scalable Model Compression by Entropy Penalized Reparameterization
Deniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava

Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
William W. Cohen, Haitian Sun, R. Alex Hofer, Matthew Siegler

Semi-Supervised Generative Modeling for Controllable Speech Synthesis
Raza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg, RJ Skerry-Ryan, Daisy Stanton, David Kao, Tom Bagby

Span Recovery for Deep Neural Networks with Applications to Input Obfuscation
Rajesh Jayaram, David Woodruff, Qiuyi Zhang

Thieves on Sesame Street! Model Extraction of BERT-based APIs
Kalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh, Nicolas Papernot, Mohit Iyyer

Thinking While Moving: Deep Reinforcement Learning with Concurrent Control
Ted Xiao, Eric Jang, Dmitry Kalashnikov, Sergey Levine, Julian Ibarz, Karol Hausman, Alexander Herzog

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
Manoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma

Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards
Allan Zhou, Eric Jang, Daniel Kappler, Alex Herzog, Mohi Khansari, Paul Wohlhart, Yunfei Bai, Mrinal Kalakrishnan, Sergey Levine, Chelsea Finn

Weakly Supervised Disentanglement with Guarantees
Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole

You Only Train Once: Loss-Conditional Training of Deep Networks
Alexey Dosovitskiy, Josip Djolonga

A Mutual Information Maximization Perspective of Language Representation Learning
Lingpeng Kong, Cyprien de Masson d’Autume, Wang Ling, Lei Yu, Zihang Dai, Dani Yogatama

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (see the blog post)
Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut

Asymptotics of Wide Networks from Feynman Diagrams
Ethan Dyer, Guy Gur-Ari

DDSP: Differentiable Digital Signal Processing
Jesse Engel, Lamtharn Hantrakul, Chenjie Gu, Adam Roberts

Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Ziyang Tang, Yihao Feng, Lihong Li, Dengyong Zhou, Qiang Liu

Dream to Control: Learning Behaviors by Latent Imagination (see the blog post)
Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi

Emergent Tool Use From Multi-Agent Autocurricula
Bowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu, Glenn Powell, Bob McGrew, Igor Mordatch

Gradientless Descent: High-Dimensional Zeroth-Order Optimization
Daniel Golovin, John Karro, Greg Kochanski, Chansoo Lee, Xingyou Song, Qiuyi (Richard) Zhang

HOPPITY: Learning Graph Transformations to Detect and Fix Bugs in Programs
Elizabeth Dinella, Hanjun Dai, Ziyang Li, Mayur Naik, Le Song, Ke Wang

Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees
Binghong Chen, Bo Dai, Qinjie Lin, Guo Ye, Han Liu, Le Song

Model Based Reinforcement Learning for Atari (see the blog post)
Łukasz Kaiser, Mohammad Babaeizadeh, Piotr Miłos, Błazej Osinski, Roy H. Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker, Henryk Michalewski

Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension
Xinyun Chen, Chen Liang, Adams Wei Yu, Denny Zhou, Dawn Song, Quoc V. Le

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Yucen Luo, Alex Beatson, Mohammad Norouzi, Jun Zhu, David Duvenaud, Ryan P. Adams, Ricky T. Q. Chen

Measuring the Reliability of Reinforcement Learning Algorithms
Stephanie C.Y. Chan, Samuel Fishman, John Canny, Anoop Korattikara, Sergio Guadarrama

Meta-Learning without Memorization
Mingzhang Yin, George Tucker, Mingyuan Zhou, Sergey Levine, Chelsea Finn

Neural Tangents: Fast and Easy Infinite Neural Networks in Python (see the blog post)
Roman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A. Alemi, Jascha Sohl-Dickstein, Samuel S. Schoenholz

Scaling Autoregressive Video Models
Dirk Weissenborn, Oscar Täckström, Jakob Uszkoreit

The Intriguing Role of Module Criticality in the Generalization of Deep Networks
Niladri Chatterji, Behnam Neyshabur, Hanie Sedghi

Reformer: The Efficient Transformer (see the blog post)
Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya

Workshops
Computer Vision for Global Challenges
Organizing Committee: Ernest Mwebaze
Advisory Committee: Timnit Gebru, John Quinn

Practical ML for Developing Countries: Learning under limited/low resource scenarios
Organizing Committee: Nyalleng Moorosi, Timnit Gebru
Program Committee: Pablo Samuel Castro, Samy Bengio
Keynote Speaker: Karmel Allison

Tackling Climate Change with Machine Learning
Organizing Committee: Moustapha Cisse
Co-Organizer: Natasha Jaques
Program Committee: John C. Platt, Kevin McCloskey, Natasha Jaques
Advisor and Panel: John C. Platt

Towards Trustworthy ML: Rethinking Security and Privacy for ML
Organizing Committee: Nicholas Carlini, Nicolas Papernot
Program Committee: Shuang Song

Source: Google AI Blog


Measuring Compositional Generalization

People are capable of learning the meaning of a new word and then applying it to other language contexts. As Lake and Baroni put it, “Once a person learns the meaning of a new verb ‘dax’, he or she can immediately understand the meaning of ‘dax twice’ and ‘sing and dax’.” Similarly, one can learn a new object shape and then recognize it with different compositions of previously learned colors or materials (e.g., in the CLEVR dataset). This is because people exhibit the capacity to understand and produce a potentially infinite number of novel combinations of known components, or as Chomsky said, to make “infinite use of finite means.” In the context of a machine learning model learning from a set of training examples, this skill is called compositional generalization.

A common approach for measuring compositional generalization in machine learning (ML) systems is to split the training and testing data based on properties that intuitively correlate with compositional structure. For instance, one approach is to split the data based on sequence length—the training set consists of short examples, while the test set consists of longer examples. Another approach uses sequence patterns, meaning the split is based on randomly assigning clusters of examples sharing the same pattern to either train or test sets. For instance, the questions "Who directed Movie1" and "Who directed Movie2" both fall into the pattern "Who directed <MOVIE>" so they would be grouped together. Yet another method uses held out primitives—some linguistic primitives are shown very rarely during training (e.g., the verb “jump”), but are very prominent in testing. While each of these experiments are useful, it is not immediately clear which experiment is a "better" measure for compositionality. Is it possible to systematically design an “optimal” compositional generalization experiment?

In “Measuring Compositional Generalization: A Comprehensive Method on Realistic Data”, we attempt to address this question by introducing the largest and most comprehensive benchmark for compositional generalization using realistic natural language understanding tasks, specifically, semantic parsing and question answering. In this work, we propose a metric—compound divergence—that allows one to quantitatively assess how much a train-test split measures the compositional generalization ability of an ML system. We analyze the compositional generalization ability of three sequence to sequence ML architectures, and find that they fail to generalize compositionally. We also are releasing the Compositional Freebase Questions dataset used in the work as a resource for researchers wishing to improve upon these results.

Measuring Compositionality

In order to measure the compositional generalization ability of a system, we start with the assumption that we understand the underlying principles of how examples are generated. For instance, we begin with the grammar rules to which we must adhere when generating questions and answers. We then draw a distinction between atoms and compounds. Atoms are the building blocks that are used to generate examples and compounds are concrete (potentially partial) compositions of these atoms. For example, in the figure below, every box is an atom (e.g., Shane Steel, brother, <entity>'s <entity>, produce, etc.), which fits together to form compounds, such as produce and <verb>, Shane Steel’s brother, Did Shane Steel’s brother produce and direct Revenge of the Spy?, etc.
Building compositional sentences (compounds) from building blocks (atoms)


An ideal compositionality experiment then should have a similar atom distribution, i.e., the distribution of words and sub-phrases in the training set is as similar as possible to their distribution in the test set, but with a different compound distribution. To measure compositional generalization on a question answering task about a movie domain, one might, for instance, have the following questions in train and test:

Train set Test set
Who directed Inception?
Did Greta Gerwig direct Goldfinger?
...
Did Greta Gerwig produce Goldfinger?
Who produced Inception?
...
While atoms such as “directed”, “Inception”, and “who <predicate> <entity>” appear in both the train and test sets, the compounds are different.

The Compositional Freebase Questions dataset

In order to conduct an accurate compositionality experiment, we created the Compositional Freebase Questions (CFQ) dataset, a simple, yet realistic, large dataset of natural language questions and answers generated from the public Freebase knowledge base. The CFQ can be used for text-in / text-out tasks, as well as semantic parsing. In our experiments, we focus on semantic parsing, where the input is a natural language question and the output is a query, which when executed against Freebase, produces the correct outcome. CFQ contains around 240k examples and almost 35k query patterns, making it significantly larger and more complex than comparable datasets — about 4 times that of WikiSQL with about 17x more query patterns than Complex Web Questions. Special care has been taken to ensure that the questions and answers are natural. We also quantify the complexity of the syntax in each example using the “complexity level” metric (L), which corresponds roughly to the depth of the parse tree, examples of which are shown below.

LQuestion → Answer
10What did Commerzbank acquire? → Eurohypo; Dresdner Bank
15Did Dianna Rhodes’s spouse produce Soldier Blue? → No
20Which costume designer of E.T. married Mannequin’s cinematographer? → Deborah Lynn Scott
40Was Weekend Cowgirls produced, directed, and written by a film editor that The Evergreen State College and Fairway Pictures employed → No
50Were It’s Not About the Shawerma, The Fifth Wall, Rick’s Canoe, White Stork Is Coming, and Blues for the Avatar executive produced, edited, directed, and written by a screenwriter’s parent? → Yes

Compositional Generalization Experiments on CFQ

For a given train-test split, if the compound distributions of the train and test sets are very similar, then their compound divergence would be close to 0, indicating that they are not difficult tests for compositional generalization. A compound divergence close to 1 means that the train-test sets have many different compounds, which makes it a good test for compositional generalization. Compound divergence thus captures the notion of "different compound distribution", as desired.

We algorithmically generate train-test splits using the CFQ dataset that have a compound divergence ranging from 0 to 0.7 (the maximum that we were able to achieve). We fix the atom divergence to be very small. Then, for each split we measure the performance of three standard ML architectures — LSTM+attention, Transformer, and Universal Transformer. The results are shown in the graph below.
Compound divergence vs accuracy for three ML architectures. There is a surprisingly strong negative correlation between compound divergence and accuracy.

We measure the performance of a model by comparing the correct answers with the output string given by the model. All models achieve an accuracy greater than 95% when the compound divergence is very low. The mean accuracy on the split with highest compound divergence is below 20% for all architectures, which means that even a large training set with a similar atom distribution between train and test is not sufficient for the architectures to generalize well. For all architectures, there is a strong negative correlation between the compound divergence and the accuracy. This seems to indicate that compound divergence successfully captures the core difficulty for these ML architectures to generalize compositionally.

Potentially promising directions for future work might be to apply unsupervised pre-training on input language or output queries, or to use more diverse or more targeted learning architectures, such as syntactic attention. It would also be interesting to apply this approach to other domains such as visual reasoning, e.g. based on CLEVR, or to extend our approach to broader subsets of language understanding, including the use of ambiguous constructs, negations, quantification, comparatives, additional languages, and other vertical domains. We hope that this work will inspire others to use this benchmark to advance the compositional generalization capabilities of learning systems.

By Marc van Zee, Software Engineer, Google Research – Brain Team

Measuring Compositional Generalization



People are capable of learning the meaning of a new word and then applying it to other language contexts. As Lake and Baroni put it, “Once a person learns the meaning of a new verb ‘dax’, he or she can immediately understand the meaning of ‘dax twice’ and ‘sing and dax’.” Similarly, one can learn a new object shape and then recognize it with different compositions of previously learned colors or materials (e.g., in the CLEVR dataset). This is because people exhibit the capacity to understand and produce a potentially infinite number of novel combinations of known components, or as Chomsky said, to make “infinite use of finite means.” In the context of a machine learning model learning from a set of training examples, this skill is called compositional generalization.

A common approach for measuring compositional generalization in machine learning (ML) systems is to split the training and testing data based on properties that intuitively correlate with compositional structure. For instance, one approach is to split the data based on sequence length — the training set consists of short examples, while the test set consists of longer examples. Another approach uses sequence patterns, meaning the split is based on randomly assigning clusters of examples sharing the same pattern to either train or test sets. For instance, the questions "Who directed Movie1" and "Who directed Movie2" both fall into the pattern "Who directed <MOVIE>" so they would be grouped together. Yet another method uses held out primitives — some linguistic primitives are shown very rarely during training (e.g., the verb “jump”), but are very prominent in testing. While each of these experiments are useful, it is not immediately clear which experiment is a "better" measure for compositionality. Is it possible to systematically design an “optimal” compositional generalization experiment?

In “Measuring Compositional Generalization: A Comprehensive Method on Realistic Data”, we attempt to address this question by introducing the largest and most comprehensive benchmark for compositional generalization using realistic natural language understanding tasks, specifically, semantic parsing and question answering. In this work, we propose a metric — compound divergence — that allows one to quantitatively assess how much a train-test split measures the compositional generalization ability of an ML system. We analyze the compositional generalization ability of three sequence to sequence ML architectures, and find that they fail to generalize compositionally. We also are releasing the Compositional Freebase Questions dataset used in the work as a resource for researchers wishing to improve upon these results.

Measuring Compositionality
In order to measure the compositional generalization ability of a system, we start with the assumption that we understand the underlying principles of how examples are generated. For instance, we begin with the grammar rules to which we must adhere when generating questions and answers. We then draw a distinction between atoms and compounds. Atoms are the building blocks that are used to generate examples and compounds are concrete (potentially partial) compositions of these atoms. For example, in the figure below, every box is an atom (e.g., Shane Steel, brother, <entity>'s <entity>, produce, etc.), which fits together to form compounds, such as produce and <verb>, Shane Steel’s brother, Did Shane Steel’s brother produce and direct Revenge of the Spy?, etc.
Building compositional sentences (compounds) from building blocks (atoms).
An ideal compositionality experiment then should have a similar atom distribution, i.e., the distribution of words and sub-phrases in the training set is as similar as possible to their distribution in the test set, but with a different compound distribution. To measure compositional generalization on a question answering task about a movie domain, one might, for instance, have the following questions in train and test:
While atoms such as “directed”, “Inception”, and “who <predicate> <entity>” appear in both the train and test sets, the compounds are different.

The Compositional Freebase Questions dataset
In order to conduct an accurate compositionality experiment, we created the Compositional Freebase Questions (CFQ) dataset, a simple, yet realistic, large dataset of natural language questions and answers generated from the public Freebase knowledge base. The CFQ can be used for text-in / text-out tasks, as well as semantic parsing. In our experiments, we focus on semantic parsing, where the input is a natural language question and the output is a query, which when executed against Freebase, produces the correct outcome. CFQ contains around 240k examples and almost 35k query patterns, making it significantly larger and more complex than comparable datasets — about 4 times that of WikiSQL with about 17x more query patterns than Complex Web Questions. Special care has been taken to ensure that the questions and answers are natural. We also quantify the complexity of the syntax in each example using the “complexity level” metric (L), which corresponds roughly to the depth of the parse tree, examples of which are shown below.
Compositional Generalization Experiments on CFQ
For a given train-test split, if the compound distributions of the train and test sets are very similar, then their compound divergence would be close to 0, indicating that they are not difficult tests for compositional generalization. A compound divergence close to 1 means that the train-test sets have many different compounds, which makes it a good test for compositional generalization. Compound divergence thus captures the notion of "different compound distribution", as desired.

We algorithmically generate train-test splits using the CFQ dataset that have a compound divergence ranging from 0 to 0.7 (the maximum that we were able to achieve). We fix the atom divergence to be very small. Then, for each split we measure the performance of three standard ML architectures — LSTM+attention, Transformer, and Universal Transformer. The results are shown in the graph below.
Compound divergence vs accuracy for three ML architectures. There is a surprisingly strong negative correlation between compound divergence and accuracy.
We measure the performance of a model by comparing the correct answers with the output string given by the model. All models achieve an accuracy greater than 95% when the compound divergence is very low. The mean accuracy on the split with highest compound divergence is below 20% for all architectures, which means that even a large training set with a similar atom distribution between train and test is not sufficient for the architectures to generalize well. For all architectures, there is a strong negative correlation between the compound divergence and the accuracy. This seems to indicate that compound divergence successfully captures the core difficulty for these ML architectures to generalize compositionally.

Potentially promising directions for future work might be to apply unsupervised pre-training on input language or output queries, or to use more diverse or more targeted learning architectures, such as syntactic attention. It would also be interesting to apply this approach to other domains such as visual reasoning, e.g. based on CLEVR, or to extend our approach to broader subsets of language understanding, including the use of ambiguous constructs, negations, quantification, comparatives, additional languages, and other vertical domains. We hope that this work will inspire others to use this benchmark to advance the compositional generalization capabilities of learning systems.

Source: Google AI Blog


ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations



Ever since the advent of BERT a year ago, natural language research has embraced a new paradigm, leveraging large amounts of existing text to pretrain a model’s parameters using self-supervision, with no data annotation required. So, rather than needing to train a machine-learning model for natural language processing (NLP) from scratch, one can start from a model primed with knowledge of a language. But, in order to improve upon this new approach to NLP, one must develop an understanding of what, exactly, is contributing to language-understanding performance — the network’s height (i.e., number of layers), its width (size of the hidden layer representations), the learning criteria for self-supervision, or something else entirely?

In “ALBERT: A Lite BERT for Self-supervised Learning of Language Representations”, accepted at ICLR 2020, we present an upgrade to BERT that advances the state-of-the-art performance on 12 NLP tasks, including the competitive Stanford Question Answering Dataset (SQuAD v2.0) and the SAT-style reading comprehension RACE benchmark. ALBERT is being released as an open-source implementation on top of TensorFlow, and includes a number of ready-to-use ALBERT pre-trained language representation models.

What Contributes to NLP Performance?
Identifying the dominant driver of NLP performance is complex — some settings are more important than others, and, as our study reveals, a simple, one-at-a-time exploration of these settings would not yield the correct answers.

The key to optimizing performance, captured in the design of ALBERT, is to allocate the model’s capacity more efficiently. Input-level embeddings (words, sub-tokens, etc.) need to learn context-independent representations, a representation for the word “bank”, for example. In contrast, hidden-layer embeddings need to refine that into context-dependent representations, e.g., a representation for “bank” in the context of financial transactions, and a different representation for “bank” in the context of river-flow management.

This is achieved by factorization of the embedding parametrization — the embedding matrix is split between input-level embeddings with a relatively-low dimension (e.g., 128), while the hidden-layer embeddings use higher dimensionalities (768 as in the BERT case, or more). With this step alone, ALBERT achieves an 80% reduction in the parameters of the projection block, at the expense of only a minor drop in performance — 80.3 SQuAD2.0 score, down from 80.4; or 67.9 on RACE, down from 68.2 — with all other conditions the same as for BERT.

Another critical design decision for ALBERT stems from a different observation that examines redundancy. Transformer-based neural network architectures (such as BERT, XLNet, and RoBERTa) rely on independent layers stacked on top of each other. However, we observed that the network often learned to perform similar operations at various layers, using different parameters of the network. This possible redundancy is eliminated in ALBERT by parameter-sharing across the layers, i.e., the same layer is applied on top of each other. This approach slightly diminishes the accuracy, but the more compact size is well worth the tradeoff. Parameter sharing achieves a 90% parameter reduction for the attention-feedforward block (a 70% reduction overall), which, when applied in addition to the factorization of the embedding parameterization, incur a slight performance drop of -0.3 on SQuAD2.0 to 80.0, and a larger drop of -3.9 on RACE score to 64.0.

Implementing these two design changes together yields an ALBERT-base model that has only 12M parameters, an 89% parameter reduction compared to the BERT-base model, yet still achieves respectable performance across the benchmarks considered. But this parameter-size reduction provides the opportunity to scale up the model again. Assuming that memory size allows, one can scale up the size of the hidden-layer embeddings by 10-20x. With a hidden-size of 4096, the ALBERT-xxlarge configuration achieves both an overall 30% parameter reduction compared to the BERT-large model, and, more importantly, significant performance gains: +4.2 on SQuAD2.0 (88.1, up from 83.9), and +8.5 on RACE (82.3, up from 73.8).

These results indicate that accurate language understanding depends on developing robust, high-capacity contextual representations. The context, modeled in the hidden-layer embeddings, captures the meaning of the words, which in turn drives the overall understanding, as directly measured by model performance on standard benchmarks.

Optimized Model Performance with the RACE Dataset
To evaluate the language understanding capability of a model, one can administer a reading comprehension test (e.g., similar to the SAT Reading Test). This can be done with the RACE dataset (2017), the largest publicly available resource for this purpose. Computer performance on this reading comprehension challenge mirrors well the language modeling advances of the last few years: a model pre-trained with only context-independent word representations scores poorly on this test (45.9; left-most bar), while BERT, with context-dependent language knowledge, scores relatively well with a 72.0. Refined BERT models, such as XLNet and RoBERTa, set the bar even higher, in the 82-83 score range. The ALBERT-xxlarge configuration mentioned above yields a RACE score in the same range (82.3), when trained on the base BERT dataset (Wikipedia and Books). However, when trained on the same larger dataset as XLNet and RoBERTa, it significantly outperforms all other approaches to date, and establishes a new state-of-the-art score at 89.4.
Machine performance on the RACE challenge (SAT-like reading comprehension). A random-guess baseline score is 25.0. The maximum possible score is 95.0.
The success of ALBERT demonstrates the importance of identifying the aspects of a model that give rise to powerful contextual representations. By focusing improvement efforts on these aspects of the model architecture, it is possible to greatly improve both the model efficiency and performance on a wide range of NLP tasks. To facilitate further advances in the field of NLP, we are open-sourcing ALBERT to the research community.

Source: Google AI Blog


Predicting the Generalization Gap in Deep Neural Networks



Deep neural networks (DNN) are the cornerstone of recent progress in machine learning, and are responsible for recent breakthroughs in a variety of tasks such as image recognition, image segmentation, machine translation and more. However, despite their ubiquity, researchers are still attempting to fully understand the underlying principles that govern them. In particular, classical theories (e.g., VC-dimension and Rademacher complexity) suggest that over-parameterized functions should generalize poorly to unseen data, yet recent work has found that massively over-parameterized functions (orders of magnitude more parameters than the number of data points) generalize well. In order to improve models, a better understanding of generalization, which can lead to more theoretically grounded and therefore more principled approaches to DNN design, is required.

An important concept for understanding generalization is the generalization gap, i.e., the difference between a model’s performance on training data and its performance on unseen data drawn from the same distribution. Significant strides have been made towards deriving better DNN generalization bounds—the upper limit to the generalization gap—but they still tend to greatly overestimate the actual generalization gap, rendering them uninformative as to why some models generalize so well. On the other hand, the notion of margin—the distance between a data point and the decision boundary—has been extensively studied in the context of shallow models such as support-vector machines, and is found to be closely related to how well these models generalize to unseen data. Because of this, the use of margin to study generalization performance has been extended to DNNs, resulting in highly refined theoretical upper bounds on the generalization gap, but has not significantly improved the ability to predict how well a model generalizes.
An example of a support-vector machine decision boundary. The hyperplane defined by w∙x-b=0 is the "decision boundary" of this linear classifier, i.e., every point x lying on the hyperplane is equally likely to be in either class under this classifier.
In our ICLR 2019 paper, “Predicting the Generalization Gap in Deep Networks with Margin Distributions”, we propose the use of a normalized margin distribution across network layers as a predictor of the generalization gap. We empirically study the relationship between the margin distribution and generalization and show that, after proper normalization of the distances, some basic statistics of the margin distributions can accurately predict the generalization gap. We also make available all the models used as a dataset for studying generalization through the Github repository.
Each plot corresponds to a convolutional neural network trained on CIFAR-10 with different classification accuracies. The probability density (y-axis) of normalized margin distributions (x-axis) at 4 layers of a network is shown for three different models with increasingly better generalization (left to right). The normalized margin distributions are strongly correlated with test accuracy, which suggests they can be used as a proxy for predicting a network's generalization gap. Please see our paper for more details on these networks.
Margin Distributions as a Predictor of Generalization
Intuitively, if the statistics of the margin distribution are truly predictive of the generalization performance, a simple prediction scheme should be able to establish the relationship. As such, we chose linear regression to be the predictor. We found that the relationship between the generalization gap and the log-transformed statistics of the margin distributions is almost perfectly linear (see figure below). In fact, the proposed scheme produces better prediction relative to other existing measures of generalization. This indicates that the margin distributions may contain important information about how deep models generalize.
Predicted generalization gap (x-axis) vs. true generalization gap (y-axis) on CIFAR-100 + ResNet-32. The points lie close to the diagonal line, which indicates that the predicted values of the log linear model fit the true generalization gap very well.
The Deep Model Generalization Dataset
In addition to our paper, we are introducing the Deep Model Generalization (DEMOGEN) dataset, which consists of of 756 trained deep models, along with their training and test performance on the CIFAR-10 and CIFAR-100 datasets. The models are variants of CNNs (with architectures that resemble Network-in-Network) and ResNet-32 with different popular regularization techniques and hyperparameter settings, inducing a wide spectrum of generalization behaviors. For example, the models of CNNs trained on CIFAR-10 have the test accuracies ranging from 60% to 90.5% with generalization gaps ranging from 1% to 35%. For details of the dataset, please see our paper or the Github repository. As part of the dataset release, we also include utilities to easily load the models and reproduce the results presented in our paper.

We hope that this research and the DEMOGEN dataset will provide the community with an accessible tool for studying generalization in deep learning without having to retrain a large number of models. We also hope that our findings will motivate further research in generalization gap predictors and margin distributions in the hidden layers.

Source: Google AI Blog


Google at ICLR 2019



This week, New Orleans, LA hosts the 7th International Conference on Learning Representations (ICLR 2019), a conference focused on how one can learn meaningful and useful representations of data for machine learning. ICLR offers conference and workshop tracks, both of which include invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction and issues regarding non-convex optimization.

At the forefront of innovation in neural networks and deep learning, Google focuses on on both theory and application, developing learning approaches to understand and generalize. As Platinum Sponsor of ICLR 2019, Google will have a strong presence with over 200 researchers attending, contributing to and learning from the broader academic research community by presenting papers and posters, in addition to participating on organizing committees and in workshops.

If you are attending ICLR 2019, we hope you'll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at ICLR 2019 in the list below (Googlers highlighted in blue).

Officers and Board Members
Hugo Larochelle, Samy Bengio, Tara Sainath

General Chair
Tara Sainath

Workshop Chairs
Been Kim, Graham Taylor

Program Committee includes:
Chelsea Finn, Dale Schuurmans, Dumitru Erhan, Katherine Heller, Lihong Li, Samy Bengio, Rohit Prabhavalkar, Alex Wiltschko, Slav Petrov, George Dahl

Oral Contributions
Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
Jacob Menick, Nal Kalchbrenner

Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Curtis Hawthorne, Andrew Stasyuk, Adam Roberts, Ian Simon, Anna Huang, Sander Dieleman, Erich Elsen, Jesse Engel, Douglas Eck

Meta-Learning Update Rules for Unsupervised Representation Learning
Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein

Posters
A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery
Ali Mousavi, Gautam Dasarathy, Richard G. Baraniuk

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
Roman Novak, Lechao Xiao, Yasaman Bahri, Jaehoon Lee, Greg Yang, Jiri Hron, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein

Diversity-Sensitive Conditional Generative Adversarial Networks
Dingdong Yang, Seunghoon Hong, Yunseok Jang, Tianchen Zhao, Honglak Lee

Diversity and Depth in Per-Example Routing Models
Prajit Ramachandran, Quoc V. Le

Eidetic 3D LSTM: A Model for Video Prediction and Beyond
Yunbo Wang, Lu Jiang, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, Li Fei-Fei

GANSynth: Adversarial Neural Audio Synthesis
Jesse Engel, Kumar Krishna Agrawal, Shuo Chen, Ishaan Gulrajani, Chris Donahue, Adam Roberts

K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew Howard

Learning to Describe Scenes with Programs
Yunchao Liu, Zheng Wu, Daniel Ritchie, William Freeman, Joshua B Tenenbaum, Jiajun Wu

Learning to Infer and Execute 3D Shape Programs
Yonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William Freeman, Joshua B Tenenbaum, Jiajun Wu

The Singular Values of Convolutional Layers
Hanie Sedghi, Vineet Gupta, Philip M. Long

Unsupervised Discovery of Parts, Structure, and Dynamics
Zhenjia Xu, Zhijian Liu, Chen Sun, Kevin Murphy, William Freeman, Joshua B Tenenbaum, Jiajun Wu

Adversarial Reprogramming of Neural Networks
Gamaleldin Elsayed, Ian Goodfellow (no longer at Google), Jascha Sohl-Dickstein

Discriminator Rejection Sampling
Ian Goodfellow (no longer at Google), Jascha Sohl-Dickstein

On Self Modulation for Generative Adversarial Networks
Ting Chen, Mario Lucic, Neil Houlsby, Sylvain Gelly

Towards GAN Benchmarks Which Require Generalization
Ishaan Gulrajani, Colin Raffel, Luke Metz

Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
David Berthelot, Colin Raffel, Aurko Roy, Ian Goodfellow (no longer at Google)

A new dog learns old tricks: RL finds classic optimization algorithms
Weiwei Kong, Christopher Liaw, Aranyak Mehta, D. Sivakumar

Contingency-Aware Exploration in Reinforcement Learning
Jongwook Choi, Yijie Guo, Marcin Moczulski, Junhyuk Oh, Neal Wu, Mohammad Norouzi, Honglak Lee

Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, Sergey Levine, Jonathan Tompson

Diversity is All You Need: Learning Skills without a Reward Function
Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz, Sergey Levine

Episodic Curiosity through Reachability
Nikolay Savinov, Anton Raichuk, Raphael Marinier, Damien Vincent, Marc Pollefeys, Timothy Lillicrap, Sylvain Gelly

Learning to Navigate the Web
Izzeddin Gur, Ulrich Rueckert, Aleksandra Faust, Dilek Hakkani-Tur

Meta-Learning Probabilistic Inference for Prediction
Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin, Richard E. Turner

Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering
Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
Ofir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine

Neural Logic Machines
Honghua Dong, Jiayuan Mao, Tian Lin, Chong Wang, Lihong Li, Dengyong Zhou

Neural Program Repair by Jointly Learning to Localize and Repair
Marko Vasic, Aditya Kanade, Petros Maniatis, David Bieber, Rishabh Singh

Optimal Completion Distillation for Sequence Learning
Sara Sabour, William Chan, Mohammad Norouzi

Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Anirudh Goyal, Philemon Brakel, William Fedus, Soumye Singhal, Timothy Lillicrap, Sergey Levine, Hugo Larochelle, Yoshua Bengio

Sample Efficient Adaptive Text-to-Speech
Yutian Chen, Yannis M Assael, Brendan Shillingford, David Budden, Scott Reed, Heiga Zen, Quan Wang, Luis C. Cobo, Andrew Trask, Ben Laurie, Caglar Gulcehre, Aaron van den Oord, Oriol Vinyals, Nando de Freitas

Synthetic Datasets for Neural Program Synthesis
Richard Shin, Neel Kant, Kavi Gupta, Chris Bender, Brandon Trabucco, Rishabh Singh, Dawn Song

The Laplacian in RL: Learning Representations with Efficient Approximations
Yifan Wu, George Tucker, Ofir Nachum

A Mean Field Theory of Batch Normalization
Greg Yang, Jeffrey Pennington, Vinay Rao, Jascha Sohl-Dickstein, Samuel S Schoenholz

Efficient Training on Very Large Corpora via Gramian Estimation
Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Li Zhang, Xinyang Yi, Lichan Hong, Ed Chi, John Anderson

Predicting the Generalization Gap in Deep Networks with Margin Distributions
Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio

InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal, Riashat Islam, DJ Strouse, Zafarali Ahmed, Hugo Larochelle, Matthew Botvinick, Sergey Levine, Yoshua Bengio

AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
Bo Chang, Minmin Chen, Eldad Haber, Ed H. Chi

Complement Objective Training
Hao-Yun Chen, Pei-Hsin Wang, Chun-Hao Liu, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan

DOM-Q-NET: Grounded RL on Structured Language
Sheng Jia, Jamie Kiros, Jimmy Ba

From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
Justin Fu, Anoop Korattikara Balan, Sergey Levine, Sergio Guadarrama

Harmonic Unpaired Image-to-image Translation
Rui Zhang, Tomas Pfister, Li-Jia Li

Hierarchical Generative Modeling for Controllable Speech Synthesis
Wei-Ning Hsu, Yu Zhang, Ron Weiss, Heiga Zen, Yonghui Wu, Yuxuan Wang, Yuan Cao, Ye Jia, Zhifeng Chen, Jonathan Shen, Patrick Nguyen, Ruoming Pang

Learning Finite State Representations of Recurrent Policy Networks
Anurag Koul, Alan Fern, Samuel Greydanus

Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks
Patrick Chen, Si Si, Sanjiv Kumar, Yang Li, Cho-Jui Hsieh

Music Transformer: Generating Music with Long-Term Structure
Chen-Zhi Anna Huang, Ashish Vaswani, Jakob Uszkoreit, Ian Simon, Curtis Hawthorne, Noam Shazeer, Andrew Dai, Matthew D Hoffman, Monica Dinculescu, Douglas Eck

Universal Transformers
Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Lukasz Kaiser

What do you learn from context? Probing for sentence structure in contextualized word representations
Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, Tom McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, Ellie Pavlick

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison

How Important Is a Neuron?
Kedar Dhamdhere, Mukund Sundararajan, Qiqi Yan

Integer Networks for Data Compression with Latent-Variable Models
Johannes Ballé, Nick Johnston, David Minnen

Modeling Uncertainty with Hedged Instance Embeddings
Seong Joon Oh, Andrew Gallagher, Kevin Murphy, Florian Schroff, Jiyan Pan, Joseph Roth

Preventing Posterior Collapse with delta-VAEs
Ali Razavi, Aaron van den Oord, Ben Poole, Oriol Vinyals

Spectral Inference Networks: Unifying Deep and Spectral Learning
David Pfau, Stig Petersen, Ashish Agarwal, David GT Barrett, Kimberly L Stachenfeld

Spreading vectors for similarity search
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou

Stochastic Prediction of Multi-Agent Interactions from Partial Observations
Chen Sun, Per Karlsson, Jiajun Wu, Joshua B Tenenbaum, Kevin Murphy

Workshops
Learning from Limited Labeled Data
Sponsored by Google

Deep Reinforcement Learning Meets Structured Prediction
Organizing Committee includes: Chen Liang
Invited Speaker: Mohammad Norouzi

Debugging Machine Learning Models
Organizing Committee includes: D. Sculley
Invited Speaker: Dan Moldovan

Structure & Priors in Reinforcement Learning (SPiRL)
Organizing Committee includes: Chelsea Finn

Task-Agnostic Reinforcement Learning (TARL)
Sponsored by Google
Organizing Committee includes: Danijar Hafner, Marc G. Bellemare
Invited Speaker: Chelsea Finn

AI for Social Good
Program Committee includes: Ernest Mwebaze

Safe Machine Learning Specification, Robustness and Assurance
Program Committee includes: Nicholas Carlini

Representation Learning on Graphs and Manifolds
Program Committee includes: Bryan Perozzi

Source: Google AI Blog


Google at ICLR 2018



This week, Vancouver, Canada hosts the 6th International Conference on Learning Representations (ICLR 2018), a conference focused on how one can learn meaningful and useful representations of data for machine learning. ICLR includes conference and workshop tracks, with invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.

At the forefront of innovation in cutting-edge technology in neural networks and deep learning, Google focuses on both theory and application, developing learning approaches to understand and generalize. As Platinum Sponsor of ICLR 2018, Google will have a strong presence with over 130 researchers attending, contributing to and learning from the broader academic research community by presenting papers and posters, in addition to participating on organizing committees and in workshops.

If you are attending ICLR 2018, we hope you'll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at ICLR 2018 in the list below (Googlers highlighted in blue)

Senior Program Chairs include:
Tara Sainath

Steering Committee includes:
Hugo Larochelle

Oral Contributions
Wasserstein Auto-Encoders
Ilya Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Scholkopf

On the Convergence of Adam and Beyond (Best Paper Award)
Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang

Beyond Word Importance: Contextual Decompositions to Extract Interactions from LSTMs
W. James Murdoch, Peter J. Liu, Bin Yu

Conference Posters
Boosting the Actor with Dual Critic
Bo Dai, Albert Shaw, Niao He, Lihong Li, Le Song

MaskGAN: Better Text Generation via Filling in the _______
William Fedus, Ian Goodfellow, Andrew M. Dai

Scalable Private Learning with PATE
Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Ulfar Erlingsson

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Yujun Lin, Song Han, Huizi Mao, Yu Wang, William J. Dally

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse

Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
Adam Roberts, Jesse Engel, Matt Hoffman

Multi-Mention Learning for Reading Comprehension with Neural Cascades
Swabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
Adams Wei Yu, David Dohan, Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le

Sensitivity and Generalization in Neural Networks: An Empirical Study
Roman Novak, Yasaman Bahri, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein

Action-dependent Control Variates for Policy Optimization via Stein Identity
Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu

An Efficient Framework for Learning Sentence Representations
Lajanugen Logeswaran, Honglak Lee

Fidelity-Weighted Learning
Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

Generating Wikipedia by Summarizing Long Sequences
Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer

Matrix Capsules with EM Routing
Geoffrey Hinton, Sara Sabour, Nicholas Frosst

Temporal Difference Models: Model-Free Deep RL for Model-Based Control
Sergey Levine, Shixiang Gu, Murtaza Dalal, Vitchyr Pong

Deep Neural Networks as Gaussian Processes
Jaehoon Lee, Yasaman Bahri, Roman Novak, Samuel L. Schoenholz, Jeffrey Pennington, Jascha Sohl-Dickstein

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence at Every Step
William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian Goodfellow

Initialization Matters: Orthogonal Predictive State Recurrent Neural Networks
Krzysztof Choromanski, Carlton Downey, Byron Boots

Learning Differentially Private Recurrent Language Models
H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang

Learning Latent Permutations with Gumbel-Sinkhorn Networks
Gonzalo Mena, David Belanger, Scott Linderman, Jasper Snoek

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
Benjamin Eysenbach, Shixiang Gu, Julian IbarzSergey Levine

Meta-Learning for Semi-Supervised Few-Shot Classification
Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Josh Tenenbaum, Hugo Larochelle, Richard Zemel

Thermometer Encoding: One Hot Way to Resist Adversarial Examples
Jacob Buckman, Aurko Roy, Colin Raffel, Ian Goodfellow

A Hierarchical Model for Device Placement
Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V. LeJeff Dean

Monotonic Chunkwise Attention
Chung-Cheng Chiu, Colin Raffel

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans

Ensemble Adversarial Training: Attacks and Defenses
Florian Tramèr, Alexey Kurakin, Nicolas Papernot, Ian Goodfellow, Dan Boneh, Patrick McDaniel

Stochastic Variational Video Prediction
Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy Campbell, Sergey Levine

Depthwise Separable Convolutions for Neural Machine Translation
Lukasz Kaiser, Aidan N. Gomez, Francois Chollet

Don’t Decay the Learning Rate, Increase the Batch Size
Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le

Generative Models of Visually Grounded Imagination
Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy

Large Scale Distributed Neural Network Training through Online Distillation
Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, Geoffrey E. Hinton

Learning a Neural Response Metric for Retinal Prosthesis
Nishal P. Shah, Sasidhar Madugula, Alan Litke, Alexander Sher, EJ Chichilnisky, Yoram Singer, Jonathon Shlens

Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
Shankar Krishnan, Ying Xiao, Rif A. Saurous

A Neural Representation of Sketch Drawings
David HaDouglas Eck

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling
Carlos Riquelme, George Tucker, Jasper Snoek

Generalizing Hamiltonian Monte Carlo with Neural Networks
Daniel Levy, Matthew D. HoffmanJascha Sohl-Dickstein

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli

On the Discrimination-Generalization Tradeoff in GANs
Pengchuan Zhang, Qiang Liu, Dengyong Zhou, Tao Xu, Xiaodong He

A Bayesian Perspective on Generalization and Stochastic Gradient Descent
Samuel L. Smith, Quoc V. Le

Learning how to Explain Neural Networks: PatternNet and PatternAttribution
Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim, Sven Dähne

Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
Víctor Campos, Brendan Jou, Xavier Giró-i-Nieto, Jordi Torres, Shih-Fu Chang

Towards Neural Phrase-based Machine Translation
Po-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng

Unsupervised Cipher Cracking Using Discrete GANs
Aidan N. Gomez, Sicong Huang, Ivan Zhang, Bryan M. Li, Muhammad Osama, Lukasz Kaiser

Variational Image Compression With A Scale Hyperprior
Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston

Workshop Posters
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
Julius Adebayo, Justin Gilmer, Ian Goodfellow, Been Kim

Stoachastic Gradient Langevin Dynamics that Exploit Neural Network Structure
Zachary Nado, Jasper Snoek, Bowen Xu, Roger Grosse, David Duvenaud, James Martens

Towards Mixed-initiative generation of multi-channel sequential structure
Anna Huang, Sherol Chen, Mark J. Nelson, Douglas Eck

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon Kleinberg

GILBO: One Metric to Measure Them All
Alexander Alemi, Ian Fischer

HoME: a Household Multimodal Environment
Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron Courville

Learning to Learn without Labels
Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein

Learning via Social Awareness: Improving Sketch Representations with Facial Feedback
Natasha Jaques, Jesse Engel, David Ha, Fred Bertsch, Rosalind Picard, Douglas Eck

Negative Eigenvalues of the Hessian in Deep Neural Networks
Guillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol

Realistic Evaluation of Semi-Supervised Learning Algorithms
Avital Oliver, Augustus Odena, Colin Raffel, Ekin Cubuk, lan Goodfellow

Winner's Curse? On Pace, Progress, and Empirical Rigor
D. Sculley, Jasper Snoek, Alex Wiltschko, Ali Rahimi

Meta-Learning for Batch Mode Active Learning
Sachin Ravi, Hugo Larochelle

To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression
Michael Zhu, Suyog Gupta

Adversarial Spheres
Justin Gilmer, Luke Metz, Fartash Faghri, Sam Schoenholz, Maithra Raghu,,Martin Wattenberg, Ian Goodfellow

Clustering Meets Implicit Generative Models
Francesco Locatello, Damien Vincent, Ilya Tolstikhin, Gunnar Ratsch, Sylvain Gelly, Bernhard Scholkopf

Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
Vitalii Zhelezniak, Dan Busbridge, April Shen, Samuel L. Smith, Nils Y. Hammerla

Learning Longer-term Dependencies in RNNs with Auxiliary Losses
Trieu Trinh, Quoc Le, Andrew Dai, Thang Luong

Graph Partition Neural Networks for Semi-Supervised Classification
Alexander Gaunt, Danny Tarlow, Marc Brockschmidt, Raquel Urtasun, Renjie Liao, Richard Zemel

Searching for Activation Functions
Prajit Ramachandran, Barret Zoph, Quoc Le

Time-Dependent Representation for Neural Event Sequence Prediction
Yang Li, Nan Du, Samy Bengio

Faster Discovery of Neural Architectures by Searching for Paths in a Large Model
Hieu Pham, Melody Guan, Barret Zoph, Quoc V. Le, Jeff Dean

Intriguing Properties of Adversarial Examples
Ekin Dogus Cubuk, Barret Zoph, Sam Schoenholz, Quoc Le

PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures
Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun

The Mirage of Action-Dependent Baselines in Reinforcement Learning
George Tucker, Surya Bhupatiraju, Shixiang Gu, Richard E. Turner, Zoubin Ghahramani, Sergey Levine

Learning to Organize Knowledge with N-Gram Machines
Fan Yang, Jiazhong Nie, William W. Cohen, Ni Lao

Online variance-reducing optimization
Nicolas Le Roux, Reza Babanezhad, Pierre-Antoine Manzagol

Google at ICLR 2018



This week, Vancouver, Canada hosts the 6th International Conference on Learning Representations (ICLR 2018), a conference focused on how one can learn meaningful and useful representations of data for machine learning. ICLR includes conference and workshop tracks, with invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.

At the forefront of innovation in cutting-edge technology in neural networks and deep learning, Google focuses on both theory and application, developing learning approaches to understand and generalize. As Platinum Sponsor of ICLR 2018, Google will have a strong presence with over 130 researchers attending, contributing to and learning from the broader academic research community by presenting papers and posters, in addition to participating on organizing committees and in workshops.

If you are attending ICLR 2018, we hope you'll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at ICLR 2018 in the list below (Googlers highlighted in blue)

Senior Program Chair:
Tara Sainath

Steering Committee includes:
Hugo Larochelle

Oral Contributions
Wasserstein Auto-Encoders
Ilya Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Scholkopf

On the Convergence of Adam and Beyond (Best Paper Award)
Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang

Beyond Word Importance: Contextual Decompositions to Extract Interactions from LSTMs
W. James Murdoch, Peter J. Liu, Bin Yu

Conference Posters
Boosting the Actor with Dual Critic
Bo Dai, Albert Shaw, Niao He, Lihong Li, Le Song

MaskGAN: Better Text Generation via Filling in the _______
William Fedus, Ian Goodfellow, Andrew M. Dai

Scalable Private Learning with PATE
Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Ulfar Erlingsson

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Yujun Lin, Song Han, Huizi Mao, Yu Wang, William J. Dally

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse

Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
Adam Roberts, Jesse Engel, Matt Hoffman

Multi-Mention Learning for Reading Comprehension with Neural Cascades
Swabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
Adams Wei Yu, David Dohan, Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le

Sensitivity and Generalization in Neural Networks: An Empirical Study
Roman Novak, Yasaman Bahri, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein

Action-dependent Control Variates for Policy Optimization via Stein Identity
Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu

An Efficient Framework for Learning Sentence Representations
Lajanugen Logeswaran, Honglak Lee

Fidelity-Weighted Learning
Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

Generating Wikipedia by Summarizing Long Sequences
Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer

Matrix Capsules with EM Routing
Geoffrey Hinton, Sara Sabour, Nicholas Frosst

Temporal Difference Models: Model-Free Deep RL for Model-Based Control
Sergey Levine, Shixiang Gu, Murtaza Dalal, Vitchyr Pong

Deep Neural Networks as Gaussian Processes
Jaehoon Lee, Yasaman Bahri, Roman Novak, Samuel L. Schoenholz, Jeffrey Pennington, Jascha Sohl-Dickstein

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence at Every Step
William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian Goodfellow

Initialization Matters: Orthogonal Predictive State Recurrent Neural Networks
Krzysztof Choromanski, Carlton Downey, Byron Boots

Learning Differentially Private Recurrent Language Models
H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang

Learning Latent Permutations with Gumbel-Sinkhorn Networks
Gonzalo Mena, David Belanger, Scott Linderman, Jasper Snoek

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
Benjamin Eysenbach, Shixiang Gu, Julian IbarzSergey Levine

Meta-Learning for Semi-Supervised Few-Shot Classification
Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Josh Tenenbaum, Hugo Larochelle, Richard Zemel

Thermometer Encoding: One Hot Way to Resist Adversarial Examples
Jacob Buckman, Aurko Roy, Colin Raffel, Ian Goodfellow

A Hierarchical Model for Device Placement
Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V. LeJeff Dean

Monotonic Chunkwise Attention
Chung-Cheng Chiu, Colin Raffel

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans

Ensemble Adversarial Training: Attacks and Defenses
Florian Tramèr, Alexey Kurakin, Nicolas Papernot, Ian Goodfellow, Dan Boneh, Patrick McDaniel

Stochastic Variational Video Prediction
Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy Campbell, Sergey Levine

Depthwise Separable Convolutions for Neural Machine Translation
Lukasz Kaiser, Aidan N. Gomez, Francois Chollet

Don’t Decay the Learning Rate, Increase the Batch Size
Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le

Generative Models of Visually Grounded Imagination
Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy

Large Scale Distributed Neural Network Training through Online Distillation
Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, Geoffrey E. Hinton

Learning a Neural Response Metric for Retinal Prosthesis
Nishal P. Shah, Sasidhar Madugula, Alan Litke, Alexander Sher, EJ Chichilnisky, Yoram Singer, Jonathon Shlens

Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
Shankar Krishnan, Ying Xiao, Rif A. Saurous

A Neural Representation of Sketch Drawings
David HaDouglas Eck

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling
Carlos Riquelme, George Tucker, Jasper Snoek

Generalizing Hamiltonian Monte Carlo with Neural Networks
Daniel Levy, Matthew D. HoffmanJascha Sohl-Dickstein

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli

On the Discrimination-Generalization Tradeoff in GANs
Pengchuan Zhang, Qiang Liu, Dengyong Zhou, Tao Xu, Xiaodong He

A Bayesian Perspective on Generalization and Stochastic Gradient Descent
Samuel L. Smith, Quoc V. Le

Learning how to Explain Neural Networks: PatternNet and PatternAttribution
Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim, Sven Dähne

Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
Víctor Campos, Brendan Jou, Xavier Giró-i-Nieto, Jordi Torres, Shih-Fu Chang

Towards Neural Phrase-based Machine Translation
Po-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng

Unsupervised Cipher Cracking Using Discrete GANs
Aidan N. Gomez, Sicong Huang, Ivan Zhang, Bryan M. Li, Muhammad Osama, Lukasz Kaiser

Variational Image Compression With A Scale Hyperprior
Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston

Workshop Posters
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
Julius Adebayo, Justin Gilmer, Ian Goodfellow, Been Kim

Stoachastic Gradient Langevin Dynamics that Exploit Neural Network Structure
Zachary Nado, Jasper Snoek, Bowen Xu, Roger Grosse, David Duvenaud, James Martens

Towards Mixed-initiative generation of multi-channel sequential structure
Anna Huang, Sherol Chen, Mark J. Nelson, Douglas Eck

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon Kleinberg

GILBO: One Metric to Measure Them All
Alexander Alemi, Ian Fischer

HoME: a Household Multimodal Environment
Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron Courville

Learning to Learn without Labels
Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein

Learning via Social Awareness: Improving Sketch Representations with Facial Feedback
Natasha Jaques, Jesse Engel, David Ha, Fred Bertsch, Rosalind Picard, Douglas Eck

Negative Eigenvalues of the Hessian in Deep Neural Networks
Guillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol

Realistic Evaluation of Semi-Supervised Learning Algorithms
Avital Oliver, Augustus Odena, Colin Raffel, Ekin Cubuk, lan Goodfellow

Winner's Curse? On Pace, Progress, and Empirical Rigor
D. Sculley, Jasper Snoek, Alex Wiltschko, Ali Rahimi

Meta-Learning for Batch Mode Active Learning
Sachin Ravi, Hugo Larochelle

To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression
Michael Zhu, Suyog Gupta

Adversarial Spheres
Justin Gilmer, Luke Metz, Fartash Faghri, Sam Schoenholz, Maithra Raghu,,Martin Wattenberg, Ian Goodfellow

Clustering Meets Implicit Generative Models
Francesco Locatello, Damien Vincent, Ilya Tolstikhin, Gunnar Ratsch, Sylvain Gelly, Bernhard Scholkopf

Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
Vitalii Zhelezniak, Dan Busbridge, April Shen, Samuel L. Smith, Nils Y. Hammerla

Learning Longer-term Dependencies in RNNs with Auxiliary Losses
Trieu Trinh, Quoc Le, Andrew Dai, Thang Luong

Graph Partition Neural Networks for Semi-Supervised Classification
Alexander Gaunt, Danny Tarlow, Marc Brockschmidt, Raquel Urtasun, Renjie Liao, Richard Zemel

Searching for Activation Functions
Prajit Ramachandran, Barret Zoph, Quoc Le

Time-Dependent Representation for Neural Event Sequence Prediction
Yang Li, Nan Du, Samy Bengio

Faster Discovery of Neural Architectures by Searching for Paths in a Large Model
Hieu Pham, Melody Guan, Barret Zoph, Quoc V. Le, Jeff Dean

Intriguing Properties of Adversarial Examples
Ekin Dogus Cubuk, Barret Zoph, Sam Schoenholz, Quoc Le

PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures
Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun

The Mirage of Action-Dependent Baselines in Reinforcement Learning
George Tucker, Surya Bhupatiraju, Shixiang Gu, Richard E. Turner, Zoubin Ghahramani, Sergey Levine

Learning to Organize Knowledge with N-Gram Machines
Fan Yang, Jiazhong Nie, William W. Cohen, Ni Lao

Online variance-reducing optimization
Nicolas Le Roux, Reza Babanezhad, Pierre-Antoine Manzagol

Source: Google AI Blog


Research at Google and ICLR 2017



This week, Toulon, France hosts the 5th International Conference on Learning Representations (ICLR 2017), a conference focused on how one can learn meaningful and useful representations of data for Machine Learning. ICLR includes conference and workshop tracks, with invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.

At the forefront of innovation in cutting-edge technology in Neural Networks and Deep Learning, Google focuses on both theory and application, developing learning approaches to understand and generalize. As Platinum Sponsor of ICLR 2017, Google will have a strong presence with over 50 researchers attending (many from the Google Brain team and Google Research Europe), contributing to and learning from the broader academic research community by presenting papers and posters, in addition to participating on organizing committees and in workshops.

If you are attending ICLR 2017, we hope you'll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at ICLR 2017 in the list below (Googlers highlighted in blue).

Area Chairs include:
George Dahl, Slav Petrov, Vikas Sindhwani

Program Chairs include:
Hugo Larochelle, Tara Sainath

Contributed Talks
Understanding Deep Learning Requires Rethinking Generalization (Best Paper Award)
Chiyuan Zhang*, Samy Bengio, Moritz Hardt, Benjamin Recht*, Oriol Vinyals

Semi-Supervised Knowledge Transfer for Deep Learning from Private Training Data (Best Paper Award)
Nicolas Papernot*, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal
Talwar


Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
Shixiang (Shane) Gu*, Timothy Lillicrap, Zoubin Ghahramani, Richard E.
Turner, Sergey Levine


Neural Architecture Search with Reinforcement Learning
Barret Zoph, Quoc Le

Posters
Adversarial Machine Learning at Scale
Alexey Kurakin, Ian J. Goodfellow, Samy Bengio

Capacity and Trainability in Recurrent Neural Networks
Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo

Improving Policy Gradient by Exploring Under-Appreciated Rewards
Ofir Nachum, Mohammad Norouzi, Dale Schuurmans

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc LeGeoffrey Hinton, Jeff Dean

Unrolled Generative Adversarial Networks
Luke Metz, Ben Poole*, David Pfau, Jascha Sohl-Dickstein

Categorical Reparameterization with Gumbel-Softmax
Eric Jang, Shixiang (Shane) Gu*, Ben Poole*

Decomposing Motion and Content for Natural Video Sequence Prediction
Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee

Density Estimation Using Real NVP
Laurent Dinh*, Jascha Sohl-Dickstein, Samy Bengio

Latent Sequence Decompositions
William Chan*, Yu Zhang*, Quoc Le, Navdeep Jaitly*

Learning a Natural Language Interface with Neural Programmer
Arvind Neelakantan*, Quoc V. Le, Martín Abadi, Andrew McCallum*, Dario
Amodei*

Deep Information Propagation
Samuel Schoenholz, Justin Gilmer, Surya Ganguli, Jascha Sohl-Dickstein

Identity Matters in Deep Learning
Moritz Hardt, Tengyu Ma

A Learned Representation For Artistic Style
Vincent Dumoulin*, Jonathon Shlens, Manjunath Kudlur

Adversarial Training Methods for Semi-Supervised Text Classification
Takeru Miyato, Andrew M. Dai, Ian Goodfellow

HyperNetworks
David Ha, Andrew Dai, Quoc V. Le

Learning to Remember Rare Events
Lukasz Kaiser, Ofir Nachum, Aurko Roy*, Samy Bengio

Workshop Track Abstracts
Particle Value Functions
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh

Neural Combinatorial Optimization with Reinforcement Learning
Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio

Short and Deep: Sketching and Neural Networks
Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar

Explaining the Learning Dynamics of Direct Feedback Alignment
Justin Gilmer, Colin Raffel, Samuel S. Schoenholz, Maithra Raghu, Jascha Sohl-Dickstein

Training a Subsampling Mechanism in Expectation
Colin Raffel, Dieterich Lawson

Tuning Recurrent Neural Networks with Reinforcement Learning
Natasha Jaques*, Shixiang (Shane) Gu*, Richard E. Turner, Douglas Eck

REBAR: Low-Variance, Unbiased Gradient Estimates for Discrete Latent Variable Models
George Tucker, Andriy Mnih, Chris J. Maddison, Jascha Sohl-Dickstein

Adversarial Examples in the Physical World
Alexey Kurakin, Ian Goodfellow, Samy Bengio

Regularizing Neural Networks by Penalizing Confident Output Distributions
Gabriel Pereyra, George Tucker, Jan Chorowski, Lukasz Kaiser, Geoffrey Hinton

Unsupervised Perceptual Rewards for Imitation Learning
Pierre Sermanet, Kelvin Xu, Sergey Levine

Changing Model Behavior at Test-time Using Reinforcement Learning
Augustus Odena, Dieterich Lawson, Christopher Olah

* Work performed while at Google
† Work performed while at OpenAI

Research at Google and ICLR 2016



This week, San Juan, Puerto Rico hosts the 4th International Conference on Learning Representations (ICLR 2016), a conference focused on how one can learn meaningful and useful representations of data for Machine Learning. ICLR includes conference and workshop tracks, with invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.

At the forefront of innovation in cutting-edge technology in Neural Networks and Deep Learning, Google focuses on both theory and application, developing learning approaches to understand and generalize. As Platinum Sponsor of ICLR 2016, Google will have a strong presence with over 40 researchers attending (many from the Google Brain team and Google DeepMind), contributing to and learning from the broader academic research community by presenting papers and posters, in addition to participating on organizing committees and in workshops.

If you are attending ICLR 2016, we hope you’ll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at ICLR 2016 in the list below (Googlers highlighted in blue).

Organizing Committee

Program Chairs
Samy Bengio, Brian Kingsbury

Area Chairs include:
John Platt, Tara Sanaith

Oral Sessions

Neural Programmer-Interpreters (Best Paper Award Recipient)
Scott Reed, Nando de Freitas

Net2Net: Accelerating Learning via Knowledge Transfer
Tianqi Chen, Ian Goodfellow, Jon Shlens

Conference Track Posters

Prioritized Experience Replay
Tom Schau, John Quan, Ioannis Antonoglou, David Silver

Reasoning about Entailment with Neural Attention
Tim Rocktäschel, Edward GrefenstetteKarl Moritz Hermann, Tomáš Kočiský, Phil Blunsom

Neural Programmer: Inducing Latent Programs With Gradient Descent
Arvind Neelakantan, Quoc Le, Ilya Sutskever

MuProp: Unbiased Backpropagation For Stochastic Neural Networks
Shixiang Gu, Sergey Levine, Ilya Sutskever, Andriy Mnih

Multi-Task Sequence to Sequence Learning
Minh-Thang Luong, Quoc LeIlya Sutskever, Oriol Vinyals, Lukasz Kaiser

A Test of Relative Similarity for Model Selection in Generative Models
Eugene Belilovsky, Wacha Bounliphone, Matthew Blaschko, Ioannis Antonoglou, Arthur Gretton

Continuous control with deep reinforcement learning
Timothy Lillicrap, Jonathan HuntAlexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra

Policy Distillation
Andrei Rusu, Sergio Gomez, Caglar Gulcehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell

Neural Random-Access Machines
Karol Kurach, Marcin Andrychowicz, Ilya Sutskever

Variable Rate Image Compression with Recurrent Neural Networks
George Toderici, Sean O'Malley, Damien Vincent, Sung Jin Hwang, Michele Covell, Shumeet Baluja, Rahul Sukthankar, David Minnen

Order Matters: Sequence to Sequence for Sets
Oriol Vinyals, Samy Bengio, Manjunath Kudlur

Grid Long Short-Term Memory
Nal Kalchbrenner, Alex Graves, Ivo Danihelka

Neural GPUs Learn Algorithms
Lukasz Kaiser, Ilya Sutskever

ACDC: A Structured Efficient Linear Layer
Marcin Moczulski, Misha Denil, Jeremy Appleyard, Nando de Freitas

Workshop Track Posters

Revisiting Distributed Synchronous SGD
Jianmin Chen, Rajat Monga, Samy Bengio, Rafal Jozefowicz

Black Box Variational Inference for State Space Models
Evan Archer, Il Memming Park, Lars Buesing, John Cunningham, Liam Paninski

A Minimalistic Approach to Sum-Product Network Learning for Real Applications
Viktoriya Krakovna, Moshe Looks

Efficient Inference in Occlusion-Aware Generative Models of Images
Jonathan Huang, Kevin Murphy

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke

Deep Autoresolution Networks
Gabriel Pereyra, Christian Szegedy

Learning visual groups from co-occurrences in space and time
Phillip Isola, Daniel Zoran, Dilip Krishnan, Edward H. Adelson

Adding Gradient Noise Improves Learning For Very Deep Networks
Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, James Martens

Adversarial Autoencoders
Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow

Generating Sentences from a Continuous Space
Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio