Hi! PARIS at ICML 2021
19 papers accepted at the international Conference on Machine Learning (ICML)
Hi! PARIS is pleased to present the work of its researchers and professors at the 38th International Conference on Machine Learning (ICML) being held this week (July 18-24, 2021).
For this edition, 19 publications were accepted by the reviewers for their significant contribution in the field of machine learning. 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 Hi! PARIS Research Affiliates cover a range of topics of AI (such as linear complexity transformers, learning from bias data, Reinforcement learning, Causal learning, Online Graph dictionary learning, domain adaption with optimal transport, etc.). Several schools of Institut Polytechnique de Paris are represented.
Congratulations to our Researchers!
École polytechnique, IP PARIS: Achille Thin, Eric Moulines, Erwan Scornet, George Dasoulas, Konstantinos Chatzikokolakis, Rémi Flamary, Szymon Majewski, Vincent Plassier
ENSAE Paris, IP PARIS: Marco Cuturi, Anna Korba, Vianney Perchet, Flore Sentenac, Meyer Scetbon
Telecom Paris, IP PARIS: Ondřej Cífka, Stephan Clémençon, Ekhine Irurozki, Rémy Leluc, Nathan Noiry, Gaël Richard, Guillaume Staerman, Yannick Guyonvarch
Here is the complete list of ICML publications for Hi! PARIS Research Affiliates:
- Relative Positional Encoding for Transformers with Linear Complexity
Antoine Liutkus (Inria) · Ondřej Cífka (Télécom Paris – IP PARIS) · Shih-Lun Wu (National Taiwan University) · Umut Simsekli (Inria/ENS) · Yi-Hsuan Yang (Academia Sinica) · Gaël Richard (Télécom Paris – IP PARIS)
Article available on http://proceedings.mlr.press/v139/liutkus21a/liutkus21a.pdf - Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Pierre Laforgue (University of Milan) · Guillaume Staerman (Télécom Paris – IP PARIS) · Stephan Clémençon (Télécom Paris – IP PARIS)
Article available on http://proceedings.mlr.press/v139/laforgue21a/laforgue21a.pdf - Feature Clustering for Support Identification in Extreme RegionsHamid Jalalzai (Inria) · Rémi Leluc (Télécom Paris – IP PARIS)
Article available on http://proceedings.mlr.press/v139/jalalzai21a/jalalzai21a.pdf - Learning from Biased Data: A Semi-Parametric Approach
Patrice Bertail (Université Paris Nanterre) · Stephan Clémençon (Télécom Paris – IP PARIS) · Yannick Guyonvarch (Télécom Paris – IP PARIS) · Nathan NOIRY (Telecom Paris – IP PARIS)
Article available on http://proceedings.mlr.press/v139/bertail21a/bertail21a.pdf - Concentric mixtures of Mallows models for top-k rankings: sampling and identifiability
Fabien Collas (BCAM) · Ekhine IRUROZKI (Telecom Paris – IP PARIS)
Article available on http://proceedings.mlr.press/v139/collas21a/collas21a.pdf - Mixed Nash Equilibria in the Adversarial Examples Game
Laurent Meunier (Facebook/Dauphine) · Meyer Scetbon (CREST, ENSAE – IP PARIS) · Rafael Pinot (Dauphine University – CEA LIST) · Jamal Atif (Université Paris-Dauphine) · Yann Chevaleyre (Univ. Paris Dauphine)
Article available on http://proceedings.mlr.press/v139/meunier21a/meunier21a.pdf - Kernel Stein Discrepancy Descent
Anna Korba (CREST, ENSAE Paris – IP PARIS) · Pierre-Cyril Aubin-Frankowski (MINES ParisTech) · Szymon Majewski (Ecole Polytechnique – IP PARIS) · Pierre Ablin (CNRS and ENS)
Article available on http://proceedings.mlr.press/v139/korba21a/korba21a.pdf - Online A-Optimal Design and Active Linear Regression
Xavier Fontaine (ENS Paris-Saclay) · Pierre Perrault (ENS Paris Saclay & Inria) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay) · Vianney Perchet (ENSAE Paris – IP PARIS & Criteo AI Lab)
Article available on http://proceedings.mlr.press/v139/fontaine21a/fontaine21a.pdf - Low-Rank Sinkhorn Factorization
Meyer Scetbon (CREST, ENSAE Paris – IP PARIS) · Marco Cuturi (Google) · Gabriel Peyré (CNRS and ENS
Article available on http://proceedings.mlr.press/v139/scetbon21a/scetbon21a.pdf - Pure Exploration and Regret Minimization in Matching Bandits
Flore Sentenac (CREST, ENSAE – IP PARIS) · Jialin Yi (London School of Economics) · Clément Calauzènes (Criteo AI Lab) · Vianney Perchet (ENSAE & Criteo AI Lab) · Milan Vojnovic (London School of Economics)
Article available on http://proceedings.mlr.press/v139/sentenac21a/sentenac21a.pdf - Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
Afsaneh Mastouri (University College London) · Yuchen Zhu (University College London) · Limor Gultchin (University of Oxford) · Anna Korba (CREST, ENSAE – IP PARIS) · Ricardo Silva (University College London) · Matt J. Kusner (University College London) · Arthur Gretton (Gatsby Computational Neuroscience Unit) · Krikamol Muandet (Max Planck Institute for Intelligent Systems)
Article available on http://proceedings.mlr.press/v139/mastouri21a/mastouri21a.pdf - Analyzing the tree-layer structure of Deep Forests
Ludovic Arnould (Sorbonne Universite) · Claire Boyer (LPSM, Sorbonne Université) · Erwan Scornet (École Polytechnique de Paris – IP PARIS)
Article available on http://proceedings.mlr.press/v139/arnould21a/arnould21a.pdf - Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
Giovanni Cherubin (Alan Turing Institute) · Konstantinos Chatzikokolakis (École polytechnique – IP PARIS) · Martin Jaggi (EPFL)
Article available on http://proceedings.mlr.press/v139/cherubin21a/cherubin21a.pdf - DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
Vincent Plassier (École polytechnique – IP PARIS) · Maxime Vono (Lagrange Mathematics and Computing Research Center) · Alain Durmus (ENS Paris Saclay) · Eric Moulines (École polytechnique – IP PARIS)
Article available on http://proceedings.mlr.press/v139/plassier21a/plassier21a.pdf - Monte Carlo Variational Auto-Encoders
Achille Thin (École polytechnique – IP PARIS) · Nikita Kotelevskii (Skolkovo Institute of Science and Technology) · Arnaud Doucet (Oxford University) · Alain Durmus (ENS Paris Saclay) · Eric Moulines (École polytechnique – IP PARIS) · Maxim Panov (Skolkovo Institute of Science and Technology)
Article available on http://proceedings.mlr.press/v139/thin21a/thin21a.pdf - Lipschitz normalization for self-attention layers with application to graph neural networks
George Dasoulas (École polytechnique – IP PARIS) · Kevin Scaman (Noah’s Ark, Huawei Technologies) · Aladin Virmaux (Huawei)
Article available on http://proceedings.mlr.press/v139/dasoulas21a/dasoulas21a.pdf - Online Graph Dictionary Learning
Cédric Vincent-Cuaz (INRIA Sophia Antipolis) · Titouan Vayer (IRISA) · Rémi Flamary (École polytechnique – IP PARIS) · Marco Corneli (Université Côte d’Azur) · Nicolas Courty (UBS)
Article available on http://proceedings.mlr.press/v139/vincent-cuaz21a/vincent-cuaz21a.pdf - Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Kilian Fatras (IRISA/INRIA) · Thibault Séjourné (CNRS, Projet NORIA, ENS, PSL) · Rémi Flamary (École polytechnique – IP PARIS) · Nicolas Courty (UBS)
Article available on http://proceedings.mlr.press/v139/fatras21a/fatras21a.pdf - Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Thomas Mesnard (DeepMind) · Theophane Weber (DeepMind) · Fabio Viola (DeepMind) · Shantanu Thakoor (DeepMind) · Alaa Saade (DeepMind) · Anna Harutyunyan (DeepMind) · Will Dabney (DeepMind) · Thomas Stepleton (DeepMind) · Nicolas Heess (DeepMind) · Arthur Guez (Google DeepMind) · Eric Moulines (École polytechnique – IP PARIS) · Marcus Hutter (DeepMind) · Lars Buesing (Deepmind) · Remi Munos (DeepMind)
Article available on http://proceedings.mlr.press/v139/mesnard21a/mesnard21a.pdf