13 Jul 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
    Mahmoud Assran, Michael Rabbat
  2. All in the (Exponential) Family: Information Geometry and Thermodynamic Variational Inference
    Robert Brekelmans, Vaden W Masrani, Frank Wood, Greg Ver Steeg, Aram Galstyan
  3. TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
    Alexander Tong, Jessie Huang, Guy Wolf, David van Dijk, Smita Krishnaswamy
  4. Representations for Stable Off-Policy Reinforcement Learning
    Dibya Ghosh, Marc Bellemare
  5. An end-to-end approach for the verification problem: learning the right distance
    Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R Devon Hjelm, Tiago Falk
  6. Universal Equivariant Multilayer Perceptrons
    Siamak Ravanbakhsh
  7. Incidence Networks for Geometric Deep Learning
    Marjan Albooyeh, Daniele Bertolini, Siamak Ravanbakhsh
  8. Latent Variable Modelling with Hyperbolic Normalizing Flows
    Joey Bose, Ariella Smofsky, Renjie Liao, Prakash PanangadenWill Hamilton
  9. Inductive Relation Prediction by Subgraph Reasoning
    Komal Teru, Etienne Denis, Will Hamilton
  10. On Variational Learning of Controllable Representations for Text without Supervision
    Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao
  11. What can I do here? A Theory of Affordances in Reinforcement Learning
    Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup
  12. Constrained Markov Decision Processes via Backward Value Functions
    Harsh Satija, Philip Amortila, Joelle Pineau
  13. Invariant Causal Prediction for Block MDPs
    Clare Lyle, Amy Zhang, Angelos Filos, Shagun Sodhani, Marta Kwiatkowska, Yarin Gal, Doina PrecupJoelle Pineau
  14. Online Learned Continual Compression with Adaptive Quantization Modules
    Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Joelle Pineau
  15. Interference and Generalization in Temporal Difference Learning
    Emmanuel Bengio, Joelle Pineau, Doina Precup
  16. Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs
    Meng Qu, Tianyu Gao, Louis-Pascal Xhonneux, Jian Tang
  17. Continuous Graph Neural Networks
    Louis-Pascal Xhonneux, Meng Qu, Jian Tang
  18. Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
    Yao Liu, Pierre-Luc Bacon, Emma Brunskill
  19. Linear Lower Bounds and Conditioning of Differentiable Games
    Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas
  20. Stochastic Hamiltonian Gradient Methods for Smooth Games
    Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal VincentSimon Lacoste-JulienIoannis Mitliagkas
  21. Countering Language Drift with Seeded Iterated Learning
    Yuchen Lu, Soumye Singhal, Florian Strub, Aaron Courville, Olivier Pietquin
  22. AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
    Jae Hyun Lim, Aaron CourvilleChristopher Pal, Chin-Wei Huang
  23. Revisiting Fundamentals of Experience Replay
    William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua BengioHugo Larochelle, Mark Rowland, Will Dabney
  24. Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
    Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio
  25. Learning to Navigate in Synthetically Accessible Chemical Space Using Reinforcement Learning
    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
  26. Small-GAN: Speeding up GAN Training using Core-Sets
    Samrath Sinha, Han Zhang, Anirudh Goyal, Yoshua BengioHugo Larochelle, Augustus Odena
  27. Perceptual Generative Autoencoders
    Zijun Zhang, Ruixiang Zhang, Zongpeng Li, Yoshua BengioLiam Paull
  28. Decoupled Greedy Learning of CNNs
    Eugene Blilovsky, Michael Eickenbert, Edouard Oyallon
  29. Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
    Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen
  30. Learning Structured Latent Factors from Dependent Data: A Generative Model Framework from Information-Theoretic Perspective
    Ruixiang Zhang, Masanori Koyama, Katsuhiko Ishiguro
  31. On Relativistic f-Divergences
    Alexia Jolicoeur-Martineau
  32. A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
    Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich
  33. A Graph to Graphs Framework for Retrosynthesis Prediction
    Chence Shi, Minkai Xu, Hongyu Guo, Ming Zhang, Jian Tang
  34. Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
    Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei


  1. Women in Machine Learning Un-Workshop
    Tatjana Chavdarova · Caroline V Weis · Amy Zhang · Fariba Yousefi · Mandana Samiei · Larissa Schiavo
  2. Graph Representation Learning and Beyond (GRL+)
    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
  3. Self-supervision in Audio and Speech
    Mirco Ravanelli · Dmitriy Serdyuk · R Devon Hjelm · Bhuvana Ramabhadran · Titouan Parcollet
  4. MLRetrospectives : A Venue for Self-Reflection in ML Research
    Jessica Forde · Jesse Dodge · Mayoore Jaiswal · Rosanne Liu · Ryan Lowe · Rosanne Liu · Joelle Pineau · Yoshua Bengio
  5. Workshop on Continual Learning
    Haytham Fayek · Arslan Chaudhry · David Lopez-Paz · Eugene Belilovsky · Jonathan Schwarz · Marc Pickett · Rahaf Aljundi · Sayna Ebrahimi · Razvan Pascanu · Puneet Dokania
  6. 4th Lifelong Learning Workshop
    Shagun Sodhani · Sarath Chandar · Balaraman Ravindran · Doina Precup
  7. INNF+: Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models
    Chin-Wei Huang · David Krueger · Rianne Van den Berg · George Papamakarios · Chris Cremer · Tian Qi Chen · Danilo J. Rezende
  8. Machine Learning for Global Health
    Danielle Belgrave · Danielle Belgrave · Stephanie Hyland · Charles Onu · Nicholas Furnham · Ernest Mwebaze · Neil Lawrence
  9. Bridge Between Perception and Reasoning: Graph Neural Networks & Beyond
    Jian Tang · Le Song · Jure Leskovec · Renjie Liao · Yujia Li · Sanja Fidler · Richard Zemel · Ruslan Salakhutdinov

Photo from: Perceptual Generative Autoencoders