NeurIPS 2020 : Les chercheurs de Mila se préparent en grand nombre

La conférence sur les systèmes de traitement de l’information neuronale (NeurIPS) a dévoilé la liste complète des publications acceptées en prévision de sa 34e édition qui sera entièrement virtuelle.

Les titulaires des chaires NeurIPS 2020 ont annoncé que sur les 12 115 publications soumises, 1 903 au total ont été acceptées pour la conférence de cette année. Ce nombre très élevé est une illustration que la culture de la recherche devient de plus en plus compétitive.

Au vu de la pression croissante à laquelle nos chercheurs sont confrontés, il est important de commémorer tout le travail que nos étudiants et professeurs ont accompli en produisant leurs recherches et en organisant des ateliers pour la conférence.

Les publications acceptées de notre communauté couvrent un éventail de sujets, y compris, mais sans s’y limiter, de nouvelles approches de méta-apprentissage continu agnostique par modèle, des solutions à l’oversmoothness dans les réseaux convolutionnels de graphes, et deux méthodes de régularisation des politiques dans l’apprentissage de renforcement profond multi-agents.

Voici la liste complète des publications acceptées, ainsi qu’un aperçu des ateliers co-organisés par des membres de Mila (en anglais) :

1. 1. 1. 1. 1. Untangling tradeoffs between recurrence and self-attention in neural networks
               Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie
               https://arxiv.org/abs/2006.09471
            2. Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
               Samarth Sinha, Zhengli Zhao, Anirudh Goyal, Colin Raffel, Augustus Odena
               https://arxiv.org/abs/2002.06224
            3. Hybrid Models for Learning to Branch
               Prateek Gupta, Maxime Gasse, Elias B. Khalil, M. Pawan Kumar, Andrea Lodi, Yoshua Bengio
               https://arxiv.org/abs/2006.15212
            4. The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
               Harm van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar
               https://arxiv.org/abs/2007.03158
            5. Your GAN is Secretly an Energy-based Model and You Should use Discriminator Latent Sampling
               Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio
               https://arxiv.org/abs/2003.06060
            6. Counterexample-Guided Learning of Monotonic Neural Networks
               Aishwarya Sivaraman, Golnoosh Farnadi, Todd Millstein, Guy Van den Broeck
               https://arxiv.org/abs/2006.08852
            7. Adversarial Example Games
               Joey Bose, Gauthier Gidel, Hugo Berard, Andre Cianflone, Pascal Vincent, Simon Lacoste-Julien, William Hamilton
               https://arxiv.org/abs/2007.00720
            8. Online Fast Adaptation and Knowledge Accumulation: A New Approach to Continual Learning
               Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexandre Lacoste, David Vazquez, Laurent Charlin
               https://arxiv.org/abs/2003.05856
            9. Learning Dynamic Belief Graphs to Generalize on Text-Based Games
               Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulás Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William Hamilton
               https://arxiv.org/abs/2002.09127
            10. Measuring Systematic Generalization in Neural Proof Generation with Transformers
                Nicolas Gontier, Koustuv Sinha, Siva Reddy, Christopher Pal
                https://arxiv.org/abs/2009.14786
            11. Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
                Dinghuai Zhang, Mao Ye, Chengyue Gong, Zhanxing Zhu, Qiang Liu
                https://arxiv.org/abs/2002.09169
            12. Forethought and Hindsight in Credit Assignment
                Veronica Chelu, Doina Precup, Hado van Hasselt
            13. Real World Games Look like Spinning Tops
                Wojciech Marian Czarnecki, Gauthier Gidel, Brendan Tracy, Karl Tuyls, Shayegan Omidshafiefi, David Balduzzi, Max Jaderberg
                https://arxiv.org/abs/2004.09468
            14. Neumann Networks: Differential programming for supervised learning with missing values
                Marine Le Morvan, Julie Josse, Thomas Moreau, Erwan Scornet, Gaël Varoquaux
                https://arxiv.org/abs/2007.01627
            15. Training Linear Finite-State Machines
                Arash Ardakani, Amir Ardakani, Warren Gross
            16. RL Unplugged: Benchmarks for Offline Reinforcement Learning
                Caglar Gulcehre, Ziyu Wang, Alexander Novikov, Tom Le Paine, Sergio Gomez Colmenarejo, Konrad Zolna, Rishabh Agarwal, Josh Merel, Daniel Mankowitz, Cosmin Paduraru, Gabriel Dulac-Arnold, Jerry Li, Mohammad Norouzi, Matt Hoffman, Ofir Nachum, George Tucker, Nicolas Heess, Nando de Freitas
                https://arxiv.org/abs/2006.13888
            17. Graph Policy Network for Transferable Active Learning on Graphs
                Shengding Hu, Zheng Xiong, Xingdi Yuan, Marc-Alexandre Côté, Zhiyuan Liu, Jian Tang
                https://arxiv.org/abs/2006.13463
            18. Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
                Wangchunshu Zhou, Jinyi Hu, Hanlin Zhang, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang
            19. Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
                Julien Roy, Paul Barde, Félix Harvey, Derek Nowrouzezahrai, Christopher Pal
                https://arxiv.org/abs/1908.02269
            20. Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
                Yimeng Min, Frederik Wenkel, Guy Wolf
                https://arxiv.org/abs/2003.08414
            21. In search of robust measures of generalization
                Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel Roy
            22. An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
                Scott Fujimoto, David Meger, Doina Precup
            23. Learning Graph Structure with A Finite-State Automaton Layer
                Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow
                https://arxiv.org/abs/2007.04929
            24. Unsupervised Learning of Dense Visual Representations
                Pedro O. Pinheiro, Amjad Almahairi, Ryan Benmalek, Florian Golemo, Aaron Courville
            25. Equivariant Networks for Hierarchical Structures
                Renhao Wang, Marjan Albooyeh, Siamak Ravanbakhsh
            26. Symbols: Probing Learning Algorithms with Synthetic Datasets
                Alexandre Lacoste, Pau Rodríguez, Frederic Branchaud-Charron, Massimo Caccia, Issam Hadj Laradji, Alexandre Drouin, Matthew Craddock, Laurent Charlin, David Vázquez
                https://arxiv.org/abs/2009.06415
            27. Explicit Regularization is Stronger than Implicit Bias: A Study of SGD around Bad Global Minima
                Shengchao Liu, Dimitris Papailiopoulos, Dimitris Achlioptas
            28. Novelty Search in representational space for sample efficient exploration
                Ruo Yu Tao, Vincent François-Lavet, Joelle Pineau
                https://arxiv.org/abs/2009.13579
            29. La-MAML: Look-ahead Meta Learning for Continual Learning
                Gunshi Gupta, Karmesh Yadav, Liam Paull
                https://arxiv.org/abs/2007.13904
            30. Adversarial Soft Advantage Fitting: Imitation Learning Without Policy Optimization
                Paul Barde, Julien Roy, Wonseok Jeon, Joelle Pineau, Christopher Pal, Derek Nowrouzezahrai
                https://arxiv.org/abs/2006.13258
            31. Differentiable Causal Discovery from Interventional Data
                Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien, Alexandre Drouin
                https://arxiv.org/abs/2007.01754
            32. Reward Propagation using Graph Convolutional Networks
                Martin Klissarov and Doina Precup
                https://arxiv.org/abs/2010.02474
            33. Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence
                Bastian Rieck, Tristan Yates, Christian Bock, Karsten Borgwardt, Guy Wolf, Nicholas Turk-Browne, Smita Krishnaswamy
                https://arxiv.org/abs/2006.07882

      Ateliers :

      1. 1. 1. Tackling Climate Change with Machine Learning
               Tegan Maharaj, Priya Donti, Lynn Kaack, Alexandre Lacoste, Andrew Ng, John Platt, Jennifer Chayes, Yoshua Bengio
               https://www.climatechange.ai/events/neurips2019.html
            2. Topological Data Analysis and Beyond
               Bastian Rieck, Frederic Chazal, Smita Krishnaswamy, Roland Kwitt, Karthikeyan Natesan Ramamurthy, Yuhei Umeda, and Guy Wolf
               https://tda-in-ml.github.io/
            3. Differential Geometry meets Deep Learning (DiffGeo4DL)
               Joey Bose, William Hamilton
               https://sites.google.com/view/diffgeo4dl/
            4. Differentiable vision, graphics, and physics applied to machine learning
               Krishna Murthy, Kelsey Allen, Victoria Dean, Johanna Hansen, Shuran Song, Florian Shkurti, Liam Paull, Derek Nowrouzezahrai, Josh Tenenbaum
               https://montrealrobotics.ca/diffcvgp/
            5. Resistance AI
               Mattie Tesfaldet, J Khadijah Abdurahman, William Agnew, Abeba Birhane, Elliot Creager, Agata Foryciarz, Pratyusha Ria Kalluri, Sayash Kapoor, Raphael Gontijo Lopes, Manuel Sabin, Marie-Therese Png, Maria Skoularidou, Ramon Vilarino, Rose E. Wang
               https://sites.google.com/view/resistance-ai-neurips-20/home
            6. Biological and Artificial Reinforcement Learning
               Raymond Chua, Feryal Behbahani, Sara Zannone, Doina Precup, Ida Momennejad, Blake Richards, Rui Ponte Costa
               https://sites.google.com/view/biologicalandartificialrl
            7. ML Retrospectives, Surveys & Meta-Analyses
               Chhavi Yadav, Prabhu Pradhan, Abhishek Gupta, Peter Henderson, Ryan Lowe, Jessica Forde, Jesse Dodge, Mayoore Jaiswal, Joelle Pineau
               https://ml-retrospectives.github.io/neurips2020/
            8. Object Representations for Learning and Reasoning
               William Agnew, Rim Assouel, Michael Chang, Antonia Creswell, Eliza Kosoy, Aravind Rajeswaran, Sjoerd van Steenkiste
               https://orlrworkshop.github.io/index.html
            9. Algorithmic Fairness through the Lens of Causality and Interpretability
               Golnoosh Farnadi, Awa Dieng, Jessica Schrouff, Matt Kusner, Fernando Diaz
               https://www.afciworkshop.org/
            10. AI for Earth Sciences
                Natasha Dudek, S. Karthik Mukkavilli, Johanna Hansen, Kelly Kochanski, S. Karthik Mukkavilli, Tom Beucler, Karthik Kashinath, Mayur Mudigonda, Amy McGovern
                https://ai4earthscience.github.io/neurips-2020-workshop/organizers.html 
            11. ML4H: Machine Learning for Health
                Benjamin Akera, Emily Alsentzer, Oliver J. Bear, Ioana Bica, Irene Chen, Fabian Falck, Stephanie Hyland, Dani Kyasseh, Matthew McDermott, Ehi Nosakhare, Charles Onu, Stephen Pfohl, Aahlad Manas Puli, Suproteem Sarkar, Allen Schmaltz
                https://ml4health.github.io/2020/pages/organizers.html
            12. Women in Machine Learning
                Amy Zhang, Elizabeth Wood, Mel Woghiren, Kristy Choi, Raquel Aoki, Judy Hanwen Shen, Belén Saldías, Xenia Miscouridou, Krystal Maughan, Xinyi Chen, Erin Grant
                https://wimlworkshop.org/neurips2020/contact-us/
            13. Offline Reinforcement Learning
                Rishabh Agarwal, Aviral Kumar, George Tucker, Doina Precup, Lihong Li
                https://offline-rl-neurips.github.io/