13
Juil
2020
34 ARTICLES ACCEPTÉES À LA CONFÉRENCE INTERNATIONALE SUR L’APPRENTISSAGE AUTOMATIQUE (ICML)
Mila, l’institut québécois d’intelligence artificielle est fier de présenter les travaux de ses chercheurs à la 37e Conférence internationale sur l’apprentissage machine (ICML) qui se tient cette semaine.
Pour cette édition, 34 publications ont été acceptées par les membres du comité d’évaluation pour leur contribution significative dans le domaine de l’apprentissage machine. En plus, plusieurs membres de Mila ont contribué à l’organisation à une dizaine d’ateliers.
La conférence ICML est mondialement reconnue pour la présentation et la publication de recherches de pointe sur tous les aspects de l’apprentissage machine, et est l’une des conférences sur l’IA qui connaît la plus forte croissance au monde.
Les articles acceptés des chercheurs de Mila couvrent un éventail de sujets, notamment l’accélération des Réseaux antagonistes génératifs, le traitement automatique du langage naturel (NLP) et des innovations utilisant l’auto-encodeur variationnel. En voici la liste complète :
- On the Convergence of Nesterov’s Accelerated Gradient Method in Stochastic Settings
Mahmoud Assran, Michael Rabbat
https://arxiv.org/abs/2002.12414 - All in the (Exponential) Family: Information Geometry and Thermodynamic Variational Inference
Robert Brekelmans, Vaden W Masrani, Frank Wood, Greg Ver Steeg, Aram Galstyan
https://icml.cc/Conferences/2020/ScheduleMultitrack?event=6234 - TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
Alexander Tong, Jessie Huang, Guy Wolf, David van Dijk, Smita Krishnaswamy
https://arxiv.org/abs/2002.04461 - Representations for Stable Off-Policy Reinforcement Learning
Dibya Ghosh, Marc Bellemare
https://proceedings.icml.cc/static/paper_files/icml/2020/5540-Paper.pdf - An end-to-end approach for the verification problem: learning the right distance
Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R Devon Hjelm, Tiago Falk
https://arxiv.org/abs/2002.09469 - Universal Equivariant Multilayer Perceptrons
Siamak Ravanbakhsh
https://arxiv.org/abs/2002.02912 - Incidence Networks for Geometric Deep Learning
Marjan Albooyeh, Daniele Bertolini, Siamak Ravanbakhsh
https://arxiv.org/abs/1905.11460 - Latent Variable Modelling with Hyperbolic Normalizing Flows
Joey Bose, Ariella Smofsky, Renjie Liao, Prakash Panangaden, Will Hamilton
https://arxiv.org/abs/2002.06336 - Inductive Relation Prediction by Subgraph Reasoning
Komal Teru, Etienne Denis, Will Hamilton
https://arxiv.org/pdf/1911.06962.pdf - On Variational Learning of Controllable Representations for Text without Supervision
Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao
https://arxiv.org/abs/1905.11975 - What can I do here? A Theory of Affordances in Reinforcement Learning
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup
https://arxiv.org/abs/2006.15085 - Constrained Markov Decision Processes via Backward Value Functions
Harsh Satija, Philip Amortila, Joelle Pineau
https://openreview.net/forum?id=S1lyyANYwr - Invariant Causal Prediction for Block MDPs
Clare Lyle, Amy Zhang, Angelos Filos, Shagun Sodhani, Marta Kwiatkowska, Yarin Gal, Doina Precup, Joelle Pineau
https://arxiv.org/abs/2003.06016 - Online Learned Continual Compression with Adaptive Quantization Modules
Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Joelle Pineau
https://arxiv.org/abs/1911.08019 - Interference and Generalization in Temporal Difference Learning
Emmanuel Bengio, Joelle Pineau, Doina Precup
https://arxiv.org/abs/2003.06350 - Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs
Meng Qu, Tianyu Gao, Louis-Pascal Xhonneux, Jian Tang
https://arxiv.org/abs/2007.02387 - Continuous Graph Neural Networks
Louis-Pascal Xhonneux, Meng Qu, Jian Tang
https://arxiv.org/abs/1912.00967 - Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Yao Liu, Pierre-Luc Bacon, Emma Brunskill
https://arxiv.org/abs/1910.06508 - Linear Lower Bounds and Conditioning of Differentiable Games
Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas
https://arxiv.org/abs/1906.07300 - Stochastic Hamiltonian Gradient Methods for Smooth Games
Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien, Ioannis Mitliagkas
https://arxiv.org/abs/2007.04202 - Countering Language Drift with Seeded Iterated Learning
Yuchen Lu, Soumye Singhal, Florian Strub, Aaron Courville, Olivier Pietquin
https://arxiv.org/abs/2003.12694 - AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
Jae Hyun Lim, Aaron Courville, Christopher Pal, Chin-Wei Huang
https://arxiv.org/abs/2006.05164 - Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua Bengio, Hugo Larochelle, Mark Rowland, Will Dabney
http://acsweb.ucsd.edu/~wfedus/pdf/replay.pdf - 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
https://arxiv.org/abs/2006.16981 - 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
https://arxiv.org/abs/2004.12485 - Small-GAN: Speeding up GAN Training using Core-Sets
Samrath Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena
https://arxiv.org/abs/1910.13540 - Perceptual Generative Autoencoders
Zijun Zhang, Ruixiang Zhang, Zongpeng Li, Yoshua Bengio, Liam Paull
https://arxiv.org/abs/1906.10335 - Decoupled Greedy Learning of CNNs
Eugene Blilovsky, Michael Eickenbert, Edouard Oyallon
https://proceedings.icml.cc/static/paper_files/icml/2020/2966-Paper.pdf - Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen
https://arxiv.org/abs/2002.08473 - Learning Structured Latent Factors from Dependent Data: A Generative Model Framework from Information-Theoretic Perspective
Ruixiang Zhang, Masanori Koyama, Katsuhiko Ishiguro
https://proceedings.icml.cc/static/paper_files/icml/2020/1111-Paper.pdf - On Relativistic f-Divergences
Alexia Jolicoeur-Martineau
https://proceedings.icml.cc/static/paper_files/icml/2020/2391-Paper.pdf - A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich
https://proceedings.icml.cc/static/paper_files/icml/2020/4675-Paper.pdf - A Graph to Graphs Framework for Retrosynthesis Prediction
Chence Shi, Minkai Xu, Hongyu Guo, Ming Zhang, Jian Tang
https://arxiv.org/abs/2003.12725 - Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei
https://proceedings.icml.cc/static/paper_files/icml/2020/5006-Paper.pdf
ATELIERS
- Women in Machine Learning Un-Workshop
Tatjana Chavdarova · Caroline V Weis · Amy Zhang · Fariba Yousefi · Mandana Samiei · Larissa Schiavo
https://icml.cc/Conferences/2020/Schedule?showEvent=7300 - 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
https://icml.cc/Conferences/2020/Schedule?showEvent=5715 - Self-supervision in Audio and Speech
Mirco Ravanelli · Dmitriy Serdyuk · R Devon Hjelm · Bhuvana Ramabhadran · Titouan Parcollet
https://icml.cc/Conferences/2020/Schedule?showEvent=5732 - 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
https://icml.cc/Conferences/2020/Schedule?showEvent=5739 - 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
https://icml.cc/Conferences/2020/Schedule?showEvent=5743 - 4th Lifelong Learning Workshop
Shagun Sodhani · Sarath Chandar · Balaraman Ravindran · Doina Precup
https://icml.cc/Conferences/2020/Schedule?showEvent=5735 - 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
https://icml.cc/Conferences/2020/Schedule?showEvent=5742 - Machine Learning for Global Health
Danielle Belgrave · Danielle Belgrave · Stephanie Hyland · Charles Onu · Nicholas Furnham · Ernest Mwebaze · Neil Lawrence
https://icml.cc/Conferences/2020/Schedule?showEvent=5728 - 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
https://icml.cc/Conferences/2020/Schedule?showEvent=5744
Photo du projet : Perceptual Generative Autoencoders https://arxiv.org/abs/1906.10335