Sylvain Gelly

Publication Activity (10 Years)

Years Active: 2005-2021
Publications (10 Years): 72

Top Topics

Image Generation

Visual Representations

Unsupervised Learning

Top Venues

Publications

Joan Puigcerver, Carlos Riquelme Ruiz, Basil Mustafa, Cédric Renggli, André Susano Pinto, Sylvain Gelly, Daniel Keysers, Neil Houlsby
Scalable Transfer Learning with Expert Models. ICLR (2021)
Vincent Dumoulin, Neil Houlsby, Utku Evci, Xiaohua Zhai, Ross Goroshin, Sylvain Gelly, Hugo Larochelle
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark. CoRR (2021)
Jessica Yung, Rob Romijnders, Alexander Kolesnikov, Lucas Beyer, Josip Djolonga, Neil Houlsby, Sylvain Gelly, Mario Lucic, Xiaohua Zhai
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size. CoRR (2021)
Vincent Dumoulin, Neil Houlsby, Utku Evci, Xiaohua Zhai, Ross Goroshin, Sylvain Gelly, Hugo Larochelle
A Unified Few-Shot Classification Benchmark to Compare Transfer and Meta Learning Approaches. NeurIPS Datasets and Benchmarks (2021)
Marcin Andrychowicz, Anton Raichuk, Piotr Stanczyk, Manu Orsini, Sertan Girgin, Raphaël Marinier, Léonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, Olivier Bachem
What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study. ICLR (2021)
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)
Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D'Amour, Dan Moldovan, Sylvain Gelly, Neil Houlsby, Xiaohua Zhai, Mario Lucic
On Robustness and Transferability of Convolutional Neural Networks. CVPR (2021)
Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly
Investigating object compositionality in Generative Adversarial Networks. Neural Networks 130 (2020)
Nicolas Brosse, Carlos Riquelme, Alice Martin, Sylvain Gelly, Eric Moulines
On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation. CoRR (2020)
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation. CoRR (2020)
Marcin Andrychowicz, Anton Raichuk, Piotr Stanczyk, Manu Orsini, Sertan Girgin, Raphaël Marinier, Léonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, Olivier Bachem
What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study. CoRR (2020)
Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Cédric Renggli, André Susano Pinto, Sylvain Gelly, Daniel Keysers, Neil Houlsby
Scalable Transfer Learning with Expert Models. CoRR (2020)
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation. J. Mach. Learn. Res. 21 (2020)
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic
On Mutual Information Maximization for Representation Learning. ICLR (2020)
Josip Djolonga, Mario Lucic, Marco Cuturi, Olivier Bachem, Olivier Bousquet, Sylvain Gelly
Precision-Recall Curves Using Information Divergence Frontiers. AISTATS (2020)
Thomas Unterthiner, Daniel Keysers, Sylvain Gelly, Olivier Bousquet, Ilya O. Tolstikhin
Predicting Neural Network Accuracy from Weights. CoRR (2020)
Karol Kurach, Anton Raichuk, Piotr Stanczyk, Michal Zajac, Olivier Bachem, Lasse Espeholt, Carlos Riquelme, Damien Vincent, Marcin Michalski, Olivier Bousquet, Sylvain Gelly
Google Research Football: A Novel Reinforcement Learning Environment. AAAI (2020)
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
A Commentary on the Unsupervised Learning of Disentangled Representations. AAAI (2020)
Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D'Amour, Dan Moldovan, Sylvain Gelly, Neil Houlsby, Xiaohua Zhai, Mario Lucic
On Robustness and Transferability of Convolutional Neural Networks. CoRR (2020)
Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby
Big Transfer (BiT): General Visual Representation Learning. ECCV (5) (2020)
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR (2020)
Hartmut Maennel, Ibrahim M. Alabdulmohsin, Ilya O. Tolstikhin, Robert J. N. Baldock, Olivier Bousquet, Sylvain Gelly, Daniel Keysers
What Do Neural Networks Learn When Trained With Random Labels? NeurIPS (2020)
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
A Commentary on the Unsupervised Learning of Disentangled Representations. CoRR (2020)
Michael Tschannen, Josip Djolonga, Marvin Ritter, Aravindh Mahendran, Neil Houlsby, Sylvain Gelly, Mario Lucic
Self-Supervised Learning of Video-Induced Visual Invariances. CVPR (2020)
Hartmut Maennel, Ibrahim M. Alabdulmohsin, Ilya O. Tolstikhin, Robert J. N. Baldock, Olivier Bousquet, Sylvain Gelly, Daniel Keysers
What Do Neural Networks Learn When Trained With Random Labels? CoRR (2020)
Octavian Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities. ICML (2019)
Josip Djolonga, Mario Lucic, Marco Cuturi, Olivier Bachem, Olivier Bousquet, Sylvain Gelly
Evaluating Generative Models Using Divergence Frontiers. CoRR (2019)
Ting Chen, Mario Lucic, Neil Houlsby, Sylvain Gelly
On Self Modulation for Generative Adversarial Networks. ICLR (Poster) (2019)
Karol Kurach, Mario Lucic, Xiaohua Zhai, Marcin Michalski, Sylvain Gelly
A Large-Scale Study on Regularization and Normalization in GANs. ICML (2019)
Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Raphaël Marinier, Marcin Michalski, Sylvain Gelly
FVD: A new Metric for Video Generation. DGS@ICLR (2019)
Karol Kurach, Anton Raichuk, Piotr Stanczyk, Michal Zajac, Olivier Bachem, Lasse Espeholt, Carlos Riquelme, Damien Vincent, Marcin Michalski, Olivier Bousquet, Sylvain Gelly
Google Research Football: A Novel Reinforcement Learning Environment. CoRR (2019)
Nikolay Savinov, Anton Raichuk, Damien Vincent, Raphaël Marinier, Marc Pollefeys, Timothy P. Lillicrap, Sylvain Gelly
Episodic Curiosity through Reachability. ICLR (Poster) (2019)
Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly
High-Fidelity Image Generation With Fewer Labels. ICML (2019)
Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly
High-Fidelity Image Generation With Fewer Labels. CoRR (2019)
Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto, Gergely Neu
Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. NeurIPS (2019)
Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, André Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, Sylvain Gelly, Neil Houlsby
The Visual Task Adaptation Benchmark. CoRR (2019)
Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain Gelly
Parameter-Efficient Transfer Learning for NLP. CoRR (2019)
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations. RML@ICLR (2019)
Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain Gelly
Parameter-Efficient Transfer Learning for NLP. ICML (2019)
Lucas Beyer, Damien Vincent, Olivier Teboul, Sylvain Gelly, Matthieu Geist, Olivier Pietquin
MULEX: Disentangling Exploitation from Exploration in Deep RL. CoRR (2019)
Octavian-Eugen Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities. CoRR (2019)
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic
On Mutual Information Maximization for Representation Learning. CoRR (2019)
Christina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya O. Tolstikhin, Ruth Urner
When can unlabeled data improve the learning rate? CoRR (2019)
Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy A. Mann, André Barreto, Sylvain Gelly, Gergely Neu
Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. CoRR (2019)
Michael Tschannen, Josip Djolonga, Marvin Ritter, Aravindh Mahendran, Neil Houlsby, Sylvain Gelly, Mario Lucic
Self-Supervised Learning of Video-Induced Visual Invariances. CoRR (2019)
Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby
Large Scale Learning of General Visual Representations for Transfer. CoRR (2019)
Samaneh Azadi, Michael Tschannen, Eric Tzeng, Sylvain Gelly, Trevor Darrell, Mario Lucic
Semantic Bottleneck Scene Generation. CoRR (2019)
Christina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya O. Tolstikhin, Ruth Urner
When can unlabeled data improve the learning rate? COLT (2019)
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations. ICML (2019)
Stanislau Semeniuta, Aliaksei Severyn, Sylvain Gelly
On Accurate Evaluation of GANs for Language Generation. CoRR (2018)
Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly
Assessing Generative Models via Precision and Recall. CoRR (2018)
Mario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet
Are GANs Created Equal? A Large-Scale Study. NeurIPS (2018)
Hartmut Maennel, Olivier Bousquet, Sylvain Gelly
Gradient Descent Quantizes ReLU Network Features. CoRR (2018)
Sylvain Gelly, Karol Kurach, Marcin Michalski, Xiaohua Zhai
MemGEN: Memory is All You Need. CoRR (2018)
Ting Chen, Mario Lucic, Neil Houlsby, Sylvain Gelly
On Self Modulation for Generative Adversarial Networks. CoRR (2018)
Francesco Locatello, Damien Vincent, Ilya O. Tolstikhin, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf
Clustering Meets Implicit Generative Models. CoRR (2018)
Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto
Temporal Difference Learning with Neural Networks - Study of the Leakage Propagation Problem. CoRR (2018)
Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly
Assessing Generative Models via Precision and Recall. NeurIPS (2018)
Karol Kurach, Mario Lucic, Xiaohua Zhai, Marcin Michalski, Sylvain Gelly
The GAN Landscape: Losses, Architectures, Regularization, and Normalization. CoRR (2018)
Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Raphaël Marinier, Marcin Michalski, Sylvain Gelly
Towards Accurate Generative Models of Video: A New Metric & Challenges. CoRR (2018)
Nikolay Savinov, Anton Raichuk, Raphaël Marinier, Damien Vincent, Marc Pollefeys, Timothy P. Lillicrap, Sylvain Gelly
Episodic Curiosity through Reachability. CoRR (2018)
Sjoerd van Steenkiste, Karol Kurach, Sylvain Gelly
A Case for Object Compositionality in Deep Generative Models of Images. CoRR (2018)
Francesco Locatello, Stefan Bauer, Mario Lucic, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations. CoRR (2018)
Francesco Locatello, Damien Vincent, Ilya O. Tolstikhin, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf
Clustering Meets Implicit Generative Models. ICLR (Workshop) (2018)
Ilya O. Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Schölkopf
Wasserstein Auto-Encoders. ICLR (2018)
Ilya O. Tolstikhin, Sylvain Gelly, Olivier Bousquet, Carl-Johann Simon-Gabriel, Bernhard Schölkopf
AdaGAN: Boosting Generative Models. CoRR (2017)
Olivier Bousquet, Sylvain Gelly, Karol Kurach, Marc Schoenauer, Michèle Sebag, Olivier Teytaud, Damien Vincent
Toward Optimal Run Racing: Application to Deep Learning Calibration. CoRR (2017)
Ilya O. Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Schölkopf
Wasserstein Auto-Encoders. CoRR (2017)
Ilya O. Tolstikhin, Sylvain Gelly, Olivier Bousquet, Carl-Johann Simon-Gabriel, Bernhard Schölkopf
AdaGAN: Boosting Generative Models. NIPS (2017)
Karol Kurach, Sylvain Gelly, Michal Jastrzebski, Philip Häusser, Olivier Teytaud, Damien Vincent, Olivier Bousquet
Better Text Understanding Through Image-To-Text Transfer. CoRR (2017)
Olivier Bousquet, Sylvain Gelly, Karol Kurach, Olivier Teytaud, Damien Vincent
Critical Hyper-Parameters: No Random, No Cry. CoRR (2017)
Mario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet
Are GANs Created Equal? A Large-Scale Study. CoRR (2017)
Sylvain Gelly, Levente Kocsis, Marc Schoenauer, Michèle Sebag, David Silver, Csaba Szepesvári, Olivier Teytaud
The grand challenge of computer Go: Monte Carlo tree search and extensions. Commun. ACM 55 (3) (2012)
Sylvain Gelly, David Silver
Monte-Carlo tree search and rapid action value estimation in computer Go. Artif. Intell. 175 (11) (2011)
Nur Merve Amil, Nicolas Bredèche, Christian Gagné, Sylvain Gelly, Marc Schoenauer, Olivier Teytaud
A Statistical Learning Perspective of Genetic Programming. EuroGP (2009)
Guillaume Chaslot, L. Chatriot, Christophe Fiter, Sylvain Gelly, Jean-Baptiste Hoock, Julien Perez, Arpad Rimmel, Olivier Teytaud
Combiner connaissances expertes, hors-ligne, transientes et en ligne pour l'exploration Monte-Carlo. Apprentissage et MC. Rev. d'Intelligence Artif. 23 (2-3) (2009)
Sylvain Gelly, Jean-Baptiste Hoock, Arpad Rimmel, Olivier Teytaud, Y. Kalemkarian
The Parallelization of Monte-Carlo Planning - Parallelization of MC-Planning. ICINCO-ICSO (2008)
Sylvain Gelly, David Silver
Achieving Master Level Play in 9 x 9 Computer Go. AAAI (2008)
Sylvain Gelly, David Silver
Combining online and offline knowledge in UCT. ICML (2007)
Yizao Wang, Sylvain Gelly
Modifications of UCT and sequence-like simulations for Monte-Carlo Go. CIG (2007)
Olivier Teytaud, Sylvain Gelly, Jérémie Mary
Active learning in regression, with application to stochastic dynamic programming. ICINCO-ICSO (2007)
Sylvain Gelly, Sylvie Ruette, Olivier Teytaud
Comparison-Based Algorithms Are Robust and Randomized Algorithms Are Anytime. Evol. Comput. 15 (4) (2007)
Olivier Teytaud, Sylvain Gelly
Nonlinear programming in approximate dynamic programming - bang-bang solutions, stock-management and unsmooth penalties. ICINCO-ICSO (2007)
Olivier Teytaud, Sylvain Gelly
DCMA: yet another derandomization in covariance-matrix-adaptation. GECCO (2007)
Sylvain Gelly, Olivier Teytaud, Christian Gagné
Resource-Aware Parameterizations of EDA. IEEE Congress on Evolutionary Computation (2006)
Sylvain Gelly, Olivier Teytaud, Nicolas Bredèche, Marc Schoenauer
Universal Consistency and Bloat in GP Some theoretical considerations about Genetic Programming from a Statistical Learning Theory viewpoint. Rev. d'Intelligence Artif. 20 (6) (2006)
Olivier Teytaud, Sylvain Gelly, Jérémie Mary
On the Ultimate Convergence Rates for Isotropic Algorithms and the Best Choices Among Various Forms of Isotropy. PPSN (2006)
Olivier Teytaud, Sylvain Gelly
General Lower Bounds for Evolutionary Algorithms. PPSN (2006)
Sylvain Gelly, Jérémie Mary, Olivier Teytaud
Learning for stochastic dynamic programming. ESANN (2006)
Sylvain Gelly, Olivier Teytaud
Bayesian Networks: a Non-Frequentist Approach for Parametrization, and a more Accurate Structural Complexity Measure Bayesian Networks Learning. Rev. d'Intelligence Artif. 20 (6) (2006)
Sylvain Gelly, Olivier Teytaud, Nicolas Bredèche, Marc Schoenauer
Apprentissage statistique et programmation génétique: la croissance du code est-elle inévitable? CAP (2005)
Sylvain Gelly, Olivier Teytaud
Statistical asymptotic and non-asymptotic consistency of bayesian networks: convergence to the right structure and consistent probability estimates. CAP (2005)
Sylvain Gelly, Olivier Teytaud, Nicolas Bredèche, Marc Schoenauer
A statistical learning theory approach of bloat. GECCO (2005)
Sylvain Gelly, Nicolas Bredèche, Michèle Sebag
From Factorial and Hierarchical HMM to Bayesian Network: A Representation Change Algorithm. SARA (2005)
Sylvain Gelly, Michèle Sebag, Nicolas Bredèche
Inférence dans les HMM hiérarchiques et factorisés : changement de représentation vers le formalisme des Réseaux Bayésiens. EGC (Ateliers) (2005)
Sylvain Gelly, Nicolas Bredèche, Michèle Sebag
HMM hiérarchiques et factorisés: mécanisme d'inférence et apprentissage à partir de peu de données. CAP (2005)
Yann Semet, Sylvain Gelly, Marc Schoenauer, Michèle Sebag
Artificial Agents and Speculative Bubbles CoRR (2005)
Sylvain Gelly, Jérémie Mary, Olivier Teytaud
Taylor-based pseudo-metrics for random process fitting in dynamic programming: expected loss minimization and risk management. CAP (2005)