34 PAPERS ACCEPTED AT THE INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML)

July 13, 2020

Mila, the Quebec AI Institute is pleased to present the work of its researchers at the 37th International Conference on Machine Learning (ICML) being held this week.

For this edition, 34 publications were accepted by the reviewers for their significant contribution in the field of machine learning. In addition, several Mila members contributed to the organization of about ten workshops.

The ICML conference is world-renowned for presenting and publishing cutting-edge research on all aspects of machine learning, and is one of the fastest growing AI conferences in the world.

Accepted papers from Mila researchers cover a range of topics, including the acceleration of Generative Antagonistic Networks, Automatic Natural Language Processing (NLP), and innovations using the Variational Auto-encoder. Here is the complete list:

  1. On the Convergence of Nesterov’s Accelerated Gradient Method in Stochastic Settings

    2. Mahmoud Assran, Michael Rabbat

    https://arxiv.org/abs/2002.12414

  2. All in the (Exponential) Family: Information Geometry and Thermodynamic Variational Inference

    3. Robert Brekelmans, Vaden W Masrani, Frank Wood, Greg Ver Steeg, Aram Galstyan

    https://icml.cc/Conferences/2020/ScheduleMultitrack?event=6234

  3. TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics

    4. Alexander Tong, Jessie Huang, Guy Wolf, David van Dijk, Smita Krishnaswamy

    https://arxiv.org/abs/2002.04461

  4. Representations for Stable Off-Policy Reinforcement Learning

    5. Dibya Ghosh, Marc Bellemare

    https://proceedings.icml.cc/static/paper_files/icml/2020/5540-Paper.pdf

  5. An end-to-end approach for the verification problem: learning the right distance

    6. Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R Devon Hjelm, Tiago Falk

    https://arxiv.org/abs/2002.09469

  6. Universal Equivariant Multilayer Perceptrons

    7. Siamak Ravanbakhsh

    https://arxiv.org/abs/2002.02912

  7. Incidence Networks for Geometric Deep Learning

    8. Marjan Albooyeh, Daniele Bertolini, Siamak Ravanbakhsh

    https://arxiv.org/abs/1905.11460

  8. Latent Variable Modelling with Hyperbolic Normalizing Flows

    9. Joey Bose, Ariella Smofsky, Renjie Liao, Prakash Panangaden, Will Hamilton

    https://arxiv.org/abs/2002.06336

  9. Inductive Relation Prediction by Subgraph Reasoning

    10. Komal Teru, Etienne Denis, Will Hamilton

    https://arxiv.org/pdf/1911.06962.pdf

  10. On Variational Learning of Controllable Representations for Text without Supervision

    11. Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao

    https://arxiv.org/abs/1905.11975

  11. What can I do here? A Theory of Affordances in Reinforcement Learning

    12. Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup

    https://arxiv.org/abs/2006.15085

  12. Constrained Markov Decision Processes via Backward Value Functions

    13. Harsh Satija, Philip Amortila, Joelle Pineau

    https://openreview.net/forum?id=S1lyyANYwr

  13. Invariant Causal Prediction for Block MDPs

    14. Clare Lyle, Amy Zhang, Angelos Filos, Shagun Sodhani, Marta Kwiatkowska, Yarin Gal, Doina Precup, Joelle Pineau

    https://arxiv.org/abs/2003.06016

  14. Online Learned Continual Compression with Adaptive Quantization Modules

    15. Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Joelle Pineau

    https://arxiv.org/abs/1911.08019

  15. Interference and Generalization in Temporal Difference Learning

    16. Emmanuel Bengio, Joelle Pineau, Doina Precup

    https://arxiv.org/abs/2003.06350

  16. Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs

    17. Meng Qu, Tianyu Gao, Louis-Pascal Xhonneux, Jian Tang

    https://arxiv.org/abs/2007.02387

  17. Continuous Graph Neural Networks

    18. Louis-Pascal Xhonneux, Meng Qu, Jian Tang

    https://arxiv.org/abs/1912.00967

  18. Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling

    19. Yao Liu, Pierre-Luc Bacon, Emma Brunskill

    https://arxiv.org/abs/1910.06508

  19. Linear Lower Bounds and Conditioning of Differentiable Games

    20. Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas

    https://arxiv.org/abs/1906.07300

  20. Stochastic Hamiltonian Gradient Methods for Smooth Games

    21. Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien, Ioannis Mitliagkas

    https://arxiv.org/abs/2007.04202

  21. Countering Language Drift with Seeded Iterated Learning

    22. Yuchen Lu, Soumye Singhal, Florian Strub, Aaron Courville, Olivier Pietquin

    https://arxiv.org/abs/2003.12694

  22. AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation

    23. Jae Hyun Lim, Aaron Courville, Christopher Pal, Chin-Wei Huang

    https://arxiv.org/abs/2006.05164

  23. Revisiting Fundamentals of Experience Replay

    24. William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua Bengio, Hugo Larochelle, Mark Rowland, Will Dabney

    https://acsweb.ucsd.edu/~wfedus/pdf/replay.pdf

  24. Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules

    25. Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio

    https://arxiv.org/abs/2006.16981

  25. Learning to Navigate in Synthetically Accessible Chemical Space Using Reinforcement Learning

    26. Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Haoran Wei, Yashaswi Pathak, Shengchao Liu, Simon Blackburn, Karam Thomas, Connor Coley, Jian Tang, Sarath Chandar, Yoshua Bengio

    https://arxiv.org/abs/2004.12485

  26. Small-GAN: Speeding up GAN Training using Core-Sets

    27. Samrath Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena

    https://arxiv.org/abs/1910.13540

  27. Perceptual Generative Autoencoders

    28. Zijun Zhang, Ruixiang Zhang, Zongpeng Li, Yoshua Bengio, Liam Paull

    https://arxiv.org/abs/1906.10335

  28. Decoupled Greedy Learning of CNNs

    29. Eugene Blilovsky, Michael Eickenbert, Edouard Oyallon

    https://proceedings.icml.cc/static/paper_files/icml/2020/2966-Paper.pdf

  29. Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

    30. Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen

    https://arxiv.org/abs/2002.08473

  30. Learning Structured Latent Factors from Dependent Data: A Generative Model Framework from Information-Theoretic Perspective

    31. Ruixiang Zhang, Masanori Koyama, Katsuhiko Ishiguro

    https://proceedings.icml.cc/static/paper_files/icml/2020/1111-Paper.pdf

  31. On Relativistic f-Divergences

    32. Alexia Jolicoeur-Martineau

    https://proceedings.icml.cc/static/paper_files/icml/2020/2391-Paper.pdf

  32. A Unified Theory of Decentralized SGD with Changing Topology and Local Updates

    33. Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich

    https://proceedings.icml.cc/static/paper_files/icml/2020/4675-Paper.pdf

  33. A Graph to Graphs Framework for Retrosynthesis Prediction

    34. Chence Shi, Minkai Xu, Hongyu Guo, Ming Zhang, Jian Tang

    https://arxiv.org/abs/2003.12725

  34. Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

    35. Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei

    https://proceedings.icml.cc/static/paper_files/icml/2020/5006-Paper.pdf

WORKSHOPS

  1. Women in Machine Learning Un-Workshop

    2. Tatjana Chavdarova · Caroline V Weis · Amy Zhang · Fariba Yousefi · Mandana Samiei · Larissa Schiavo

    https://icml.cc/Conferences/2020/Schedule?showEvent=7300

  2. Graph Representation Learning and Beyond (GRL+)

    3. Petar Veličković · Michael M. Bronstein · Andreea Deac · Will Hamilton · Jessica Hamrick · Milad Hashemi · Stefanie Jegelka · Jure Leskovec · Renjie Liao · Federico Monti · Yizhou Sun · Kevin Swersky · Rex (Zhitao) Ying · Marinka Žitnik

    https://icml.cc/Conferences/2020/Schedule?showEvent=5715

  3. Self-supervision in Audio and Speech

    4. Mirco Ravanelli · Dmitriy Serdyuk · R Devon Hjelm · Bhuvana Ramabhadran · Titouan Parcollet

    https://icml.cc/Conferences/2020/Schedule?showEvent=5732

  4. MLRetrospectives : A Venue for Self-Reflection in ML Research

    5. Jessica Forde · Jesse Dodge · Mayoore Jaiswal · Rosanne Liu · Ryan Lowe · Rosanne Liu · Joelle Pineau · Yoshua Bengio

    https://icml.cc/Conferences/2020/Schedule?showEvent=5739

  5. Workshop on Continual Learning

    6. Haytham Fayek · Arslan Chaudhry · David Lopez-Paz · Eugene Belilovsky · Jonathan Schwarz · Marc Pickett · Rahaf Aljundi · Sayna Ebrahimi · Razvan Pascanu · Puneet Dokania

    https://icml.cc/Conferences/2020/Schedule?showEvent=5743

  6. 4th Lifelong Learning Workshop

    7. Shagun Sodhani · Sarath Chandar · Balaraman Ravindran · Doina Precup

    https://icml.cc/Conferences/2020/Schedule?showEvent=5735

  7. INNF+: Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models

    8. Chin-Wei Huang · David Krueger · Rianne Van den Berg · George Papamakarios · Chris Cremer · Tian Qi Chen · Danilo J. Rezende

    https://icml.cc/Conferences/2020/Schedule?showEvent=5742

  8. Machine Learning for Global Health

    9. Danielle Belgrave · Danielle Belgrave · Stephanie Hyland · Charles Onu · Nicholas Furnham · Ernest Mwebaze · Neil Lawrence

    https://icml.cc/Conferences/2020/Schedule?showEvent=5728

  9. Bridge Between Perception and Reasoning: Graph Neural Networks & Beyond

    10. Jian Tang · Le Song · Jure Leskovec · Renjie Liao · Yujia Li · Sanja Fidler · Richard Zemel · Ruslan Salakhutdinov

    https://icml.cc/Conferences/2020/Schedule?showEvent=5744

Photo from: Perceptual Generative Autoencoders https://arxiv.org/abs/1906.10335