Research Blog: Google at ICML 2017

Machine learning (ML) is a key strategic focus at Google, with highly active groups pursuing research in virtually all aspects of the field, including deep learning and more classical algorithms, exploring theory as well as application. We utilize scalable tools and architectures to build machine learning systems that enable us to solve deep scientific and engineering challenges in areas of language, speech, translation, music, visual processing and more.

As a leader in ML research, Google is proud to be a Platinum Sponsor of the thirty-fourth International Conference on Machine Learning (ICML 2017), a premier annual event supported by the International Machine Learning Society taking place this week in Sydney, Australia. With over 130 Googlers attending the conference to present publications and host workshops, we look forward to our continued colalboration with the larger ML research community.

If you’re attending ICML 2017, we hope you’ll visit the Google booth and talk with our researchers to learn more about the exciting work, creativity and fun that goes into solving some of the field’s most interesting challenges. Our researchers will also be available to talk about and demo several recent efforts, including the technology behind Facets, neural audio synthesis with Nsynth, a Q&A session on the Google Brain Residency program and much more. You can also learn more about our research being presented at ICML 2017 in the list below (Googlers highlighted in blue).

ICML 2017 Committees
Senior Program Committee includes: Alex Kulesza, Amr Ahmed, Andrew Dai, Corinna Cortes, George Dahl, Hugo Larochelle, Matthew Hoffman, Maya Gupta, Moritz Hardt, Quoc Le

Sponsorship Co-Chair: Ryan Adams

Robust Adversarial Reinforcement Learning
Lerrel Pinto, James Davidson, Rahul Sukthankar, Abhinav Gupta

Tight Bounds for Approximate Carathéodory and Beyond
Vahab Mirrokni, Renato Leme, Adrian Vladu, Sam Wong

Sharp Minima Can Generalize For Deep Nets
Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio

Geometry of Neural Network Loss Surfaces via Random Matrix Theory
Jeffrey Pennington, Yasaman Bahri

Conditional Image Synthesis with Auxiliary Classifier GANs
Augustus Odena, Christopher Olah, Jon Shlens

Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo
Matthew D. Hoffman

On the Expressive Power of Deep Neural Networks
Maithra Raghu, Ben Poole, Surya Ganguli, Jon Kleinberg, Jascha Sohl-Dickstein

AdaNet: Adaptive Structural Learning of Artificial Neural Networks
Corinna Cortes, Xavi Gonzalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang

Learned Optimizers that Scale and Generalize
Olga Wichrowska, Niru Maheswaranathan, Matthew Hoffman, Sergio Gomez, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein

Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
Satyen Kale, Zohar Karnin, Tengyuan Liang, David Pal

Algorithms for ℓp Low-Rank Approximation
Flavio Chierichetti, Sreenivas Gollapudi, Ravi Kumar, Silvio Lattanzi, Rina Panigrahy, David Woodruff

Consistent k-Clustering
Silvio Lattanzi, Sergei Vassilvitskii

Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
Jakob Foerster, Justin Gilmer, Jan Chorowski, Jascha Sohl-Dickstein, David Sussillo

Online and Linear-Time Attention by Enforcing Monotonic Alignments
Colin RaffelThang Luong, Peter Liu, Ron Weiss, Douglas Eck

Gradient Boosted Decision Trees for High Dimensional Sparse Output
Si Si, Huan Zhang, Sathiya Keerthi, Dhruv Mahajan, Inderjit Dhillon, Cho-Jui Hsieh

Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control
Natasha Jaques, Shixiang Gu, Dzmitry Bahdanau, Jose Hernandez-Lobato, Richard E Turner, Douglas Eck

Uniform Convergence Rates for Kernel Density Estimation
Heinrich Jiang

Density Level Set Estimation on Manifolds with DBSCAN
Heinrich Jiang

Maximum Selection and Ranking under Noisy Comparisons
Moein Falahatgar, Alon Orlitsky, Venkatadheeraj Pichapati, Ananda Suresh

Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Cinjon Resnick, Adam Roberts, Jesse Engel, Douglas Eck, Sander Dieleman, Karen Simonyan, Mohammad Norouzi

Distributed Mean Estimation with Limited Communication
Ananda Suresh, Felix Yu, Sanjiv Kumar, Brendan McMahan

Learning to Generate Long-term Future via Hierarchical Prediction
Ruben Villegas, Jimei Yang, Yuliang Zou, Sungryull Sohn, Xunyu Lin, Honglak Lee

Variational Boosting: Iteratively Refining Posterior Approximations
Andrew Miller, Nicholas J Foti, Ryan Adams

RobustFill: Neural Program Learning under Noisy I/O
Jacob Devlin, Jonathan Uesato, Surya Bhupatiraju, Rishabh Singh, Abdel-rahman Mohamed, Pushmeet Kohli

A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
Jayadev Acharya, Hirakendu Das, Alon Orlitsky, Ananda Suresh

Axiomatic Attribution for Deep Networks
Ankur Taly, Qiqi Yan,,Mukund Sundararajan

Differentiable Programs with Neural Libraries
Alex L Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow

Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data
Manzil Zaheer, Amr Ahmed, Alex Smola

Device Placement Optimization with Reinforcement Learning
Azalia Mirhoseini, Hieu Pham, Quoc Le, Benoit Steiner, Mohammad Norouzi, Rasmus Larsen, Yuefeng Zhou, Naveen Kumar, Samy Bengio, Jeff Dean

Canopy — Fast Sampling with Cover Trees
Manzil Zaheer, Satwik Kottur, Amr Ahmed, Jose Moura, Alex Smola

Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
Junhyuk Oh, Satinder Singh, Honglak Lee, Pushmeet Kohli

Probabilistic Submodular Maximization in Sub-Linear Time
Serban Stan, Morteza Zadimoghaddam, Andreas Krause, Amin Karbasi

Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
Michael Gygli, Mohammad Norouzi, Anelia Angelova

Stochastic Generative Hashing
Bo Dai, Ruiqi Guo, Sanjiv Kumar, Niao He, Le Song

Accelerating Eulerian Fluid Simulation With Convolutional Networks
Jonathan Tompson, Kristofer D Schlachter, Pablo Sprechmann, Ken Perlin

Large-Scale Evolution of Image Classifiers
Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc Le, Alexey Kurakin

Neural Message Passing for Quantum Chemistry
Justin Gilmer, Samuel Schoenholz, Patrick Riley, Oriol Vinyals, George Dahl

Neural Optimizer Search with Reinforcement Learning
Irwan BelloBarret Zoph, Vijay Vasudevan, Quoc Le

Implicit Generative Models
Organizers include: Ian Goodfellow

Learning to Generate Natural Language
Accepted Papers include:
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Louis Shao, Stephan Gouws, Denny Britz, Anna Goldie, Brian Strope, Ray Kurzweil

Lifelong Learning: A Reinforcement Learning Approach
Accepted Papers include:
Bridging the Gap Between Value and Policy Based Reinforcement Learning
Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans

Principled Approaches to Deep Learning
Organizers include: Robert Gens
Program Committee includes: Jascha Sohl-Dickstein

Workshop on Human Interpretability in Machine Learning (WHI)
Organizers include: Been Kim

ICML Workshop on TinyML: ML on a Test-time Budget for IoT, Mobiles, and Other Applications
Invited speakers include: Sujith Ravi

Deep Structured Prediction
Organizers include: Gal Chechik, Ofer Meshi
Program Committee includes: Vitaly Kuznetsov, Kevin Murphy
Invited Speakers include: Ryan Adams
Accepted Papers include:
Filtering Variational Objectives
Chris J Maddison, Dieterich Lawson, George Tucker, Mohammad Norouzi, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
George Tucker, Andriy Mnih, Chris J Maddison, Dieterich Lawson, Jascha Sohl-Dickstein

Machine Learning in Speech and Language Processing
Organizers include: Tara Sainath
Invited speakers include: Ron Weiss

Picky Learners: Choosing Alternative Ways to Process Data
Invited speakers include: Tomer Koren
Organizers include: Corinna Cortes, Mehryar Mohri

Private and Secure Machine Learning
Keynote Speakers include: Ilya Mironov

Reproducibility in Machine Learning Research
Invited Speakers include: Hugo Larochelle, Francois Chollet
Organizers include: Samy Bengio

Time Series Workshop
Organizers include: Vitaly Kuznetsov

Interpretable Machine Learning
Presenters include: Been Kim