Sylvain Gelly

发表

Change Point Detection and Meta-Bandits for Online Learning in Dynamic Environments

Michèle Sebag, Olivier Teytaud, Cédric Hartland, 2007 .

Inférence dans les HMM hiérarchiques et factorisés : changement de représentation vers le formalisme des Réseaux Bayésiens

Michèle Sebag, Sylvain Gelly, Nicolas Bredèche, 2005, EGC.

Bayesian Networks: a Non-Frequentist Approach for Parametrization, and a more Accurate Structural Complexity Measure Bayesian Networks Learning

Olivier Teytaud, Sylvain Gelly, S. Gelly, 2006, Rev. d'Intelligence Artif..

Gradient Descent Quantizes ReLU Network Features pdf

Sylvain Gelly, Hartmut Maennel, Olivier Bousquet, 2018, ArXiv.

Apprentissage statistique et programmation génétique: la croissance du code est-elle inévitable?

Olivier Teytaud, Marc Schoenauer, Sylvain Gelly, 2005, CAP.

A Statistical Learning Perspective of Genetic Programming

Christian Gagné, Olivier Teytaud, Marc Schoenauer, 2009, EuroGP.

Multi-armed Bandit, Dynamic Environments and Meta-Bandits

Michèle Sebag, Olivier Teytaud, Cédric Hartland, 2006 .

When can unlabeled data improve the learning rate?

Shai Ben-David, Ruth Urner, Olivier Bousquet, 2019, COLT.

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

Xiaohua Zhai, Lucas Beyer, Maxim Neumann, 2019 .

Are GANs Created Equal? A Large-Scale Study

Mario Lucic, Sylvain Gelly, Olivier Bousquet, 2017, NeurIPS.

HMM hiérarchiques et factorisés: mécanisme d'inférence et apprentissage à partir de peu de données

Michèle Sebag, Sylvain Gelly, Nicolas Bredèche, 2005, CAP.

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation pdf

Francesco Locatello, Olivier Bachem, Mario Lucic, 2020, J. Mach. Learn. Res..

The grand challenge of computer Go

Michèle Sebag, Olivier Teytaud, Marc Schoenauer, 2012, Commun. ACM.

Robust Optimizers for Nonlinear Programming in Approximate Dynamic Programming

Olivier Teytaud, Sylvain Gelly, S. Gelly, 2009 .

A Large-Scale Study on Regularization and Normalization in GANs

Xiaohua Zhai, Mario Lucic, Sylvain Gelly, 2018, ICML.

A Case for Object Compositionality in Deep Generative Models of Images pdf

Sjoerd van Steenkiste, Sylvain Gelly, Karol Kurach, 2018, ArXiv.

What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study pdf

Marcin Andrychowicz, Matthieu Geist, Olivier Pietquin, 2020, ArXiv.

Google Research Football: A Novel Reinforcement Learning Environment pdf

Olivier Bachem, Olivier Bousquet, Sylvain Gelly, 2020, AAAI.

On the Ultimate Convergence Rates for Isotropic Algorithms and the Best Choices Among Various Forms of Isotropy

Olivier Teytaud, Sylvain Gelly, Jérémie Mary, 2006, PPSN.

On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation pdf

Sylvain Gelly, Nicolas Brosse, Eric Moulines, 2020, ArXiv.

MULEX: Disentangling Exploitation from Exploration in Deep RL pdf

Lucas Beyer, Matthieu Geist, Olivier Pietquin, 2019, ArXiv.

Monte-Carlo Tree Search

Olivier Teytaud, Sylvain Gelly, Romaric Gaudel, 2012 .

Modification of UCT with Patterns in Monte-Carlo Go

Olivier Teytaud, Sylvain Gelly, Rémi Munos, 2006 .

A statistical learning theory approach of bloat

Olivier Teytaud, Marc Schoenauer, Sylvain Gelly, 2005, GECCO '05.

Predicting Neural Network Accuracy from Weights pdf

Daniel Keysers, Olivier Bousquet, Sylvain Gelly, 2020, ArXiv.

Investigating object compositionality in Generative Adversarial Networks

Sjoerd van Steenkiste, Jurgen Schmidhuber, Sylvain Gelly, 2020, Neural Networks.

On Accurate Evaluation of GANs for Language Generation pdf

Stanislau Semeniuta, Sylvain Gelly, Aliaksei Severyn, 2018, ArXiv.

OpenDP a free Reinforcement Learning toolbox for discrete time control problems

Olivier Teytaud, Sylvain Gelly, 2006, NIPS 2006.

On Self Modulation for Generative Adversarial Networks pdf

Ting Chen, Mario Lucic, Neil Houlsby, 2018, ICLR.

Competitive Training of Mixtures of Independent Deep Generative Models

Gunnar Rätsch, Bernhard Schölkopf, Francesco Locatello, 2018 .

Toward Optimal Run Racing: Application to Deep Learning Calibration pdf

Michèle Sebag, Olivier Teytaud, Marc Schoenauer, 2017, ArXiv.

Modifications of UCT and sequence-like simulations for Monte-Carlo Go

Sylvain Gelly, Yizao Wang, S. Gelly, 2007, 2007 IEEE Symposium on Computational Intelligence and Games.

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

Gary Bécigneul, Sylvain Gelly, Octavian-Eugen Ganea, 2019, ICML.

Taylor-based pseudo-metrics for random process fitting in dynamic programming: expected loss minimization and risk management

Olivier Teytaud, Sylvain Gelly, Jérémie Mary, 2005, CAP.

Better Text Understanding Through Image-To-Text Transfer pdf

Olivier Teytaud, Sylvain Gelly, Olivier Bousquet, 2017, ArXiv.

Wasserstein Auto-Encoders pdf

Bernhard Schölkopf, Sylvain Gelly, Olivier Bousquet, 2017, ICLR.

Self-Supervised Learning of Video-Induced Visual Invariances

Michael Tschannen, Mario Lucic, Marvin Ritter, 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Monte-Carlo tree search and rapid action value estimation in computer Go

David Silver, Sylvain Gelly, D. Silver, 2011, Artif. Intell..

Towards Accurate Generative Models of Video: A New Metric & Challenges pdf

Sjoerd van Steenkiste, Raphaël Marinier, Sylvain Gelly, 2018, ArXiv.

On Mutual Information Maximization for Representation Learning pdf

Michael Tschannen, Mario Lucic, Sylvain Gelly, 2019, ICLR.

Evaluating Generative Models Using Divergence Frontiers pdf

Olivier Bachem, Marco Cuturi, Mario Lucic, 2019, ArXiv.

DCMA: yet another derandomization in covariance-matrix-adaptation

Olivier Teytaud, Sylvain Gelly, S. Gelly, 2007, GECCO '07.

From Factorial and Hierarchical HMM to Bayesian Network: A Representation Change Algorithm

Michèle Sebag, Sylvain Gelly, Nicolas Bredèche, 2005, SARA.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale pdf

Georg Heigold, Lucas Beyer, Alexey Dosovitskiy, 2020, ArXiv.

New Results - Machine Learning for Stochastic Optimisation

Michèle Sebag, Olivier Teytaud, Anne Auger, 2007 .

AdaGAN: Boosting Generative Models

Bernhard Schölkopf, Sylvain Gelly, Olivier Bousquet, 2017, NIPS.

The GAN Landscape: Losses, Architectures, Regularization, and Normalization pdf

Xiaohua Zhai, Mario Lucic, Sylvain Gelly, 2018, ArXiv.

Introduction de connaissances expertes en Bandit-Based Monte-Carlo Planning avec application au Computer-Go

Olivier Teytaud, Sylvain Gelly, Arpad Rimmel, 2008 .

Learning for stochastic dynamic programming

Olivier Teytaud, Sylvain Gelly, Jérémie Mary, 2006, ESANN.

General Lower Bounds for Evolutionary Algorithms

Olivier Teytaud, Sylvain Gelly, S. Gelly, 2006, PPSN.

Episodic Curiosity through Reachability pdf

Marc Pollefeys, Nikolay Savinov, Timothy Lillicrap, 2018, ICLR.

A Commentary on the Unsupervised Learning of Disentangled Representations pdf

Gunnar Rätsch, Bernhard Schölkopf, Francesco Locatello, 2020, AAAI.

FVD: A new Metric for Video Generation

Sjoerd van Steenkiste, Raphaël Marinier, Sylvain Gelly, 2019, DGS@ICLR.

Active learning in regression, with application to stochastic dynamic programming

Olivier Teytaud, Sylvain Gelly, Jérémie Mary, 2007, ICINCO-ICSO.

Parameter-Efficient Transfer Learning for NLP

Mona Attariyan, Stanislaw Jastrzebski, Neil Houlsby, 2019, ICML.

Universal Consistency and Bloat in GP Some theoretical considerations about Genetic Programming from a Statistical Learning Theory viewpoint

Olivier Teytaud, Marc Schoenauer, Sylvain Gelly, 2006, Rev. d'Intelligence Artif..

Nonlinear programming in approximate dynamic programming - bang-bang solutions, stock-management and unsmooth penalties

Olivier Teytaud, Sylvain Gelly, S. Gelly, 2007, ICINCO-ICSO.

Precision-Recall Curves Using Information Divergence Frontiers

Olivier Bachem, Marco Cuturi, Mario Lucic, 2019, AISTATS.

Comparison-Based Algorithms Are Robust and Randomized Algorithms Are Anytime

Olivier Teytaud, Sylvain Gelly, Sylvie Ruette, 2007, Evolutionary Computation.

Clustering Meets Implicit Generative Models pdf

Gunnar Rätsch, Bernhard Schölkopf, Francesco Locatello, 2018, ICLR.

Artificial Agents and Speculative Bubbles pdf

Michèle Sebag, Marc Schoenauer, Sylvain Gelly, 2004, ArXiv.

Assessing Generative Models via Precision and Recall

Olivier Bachem, Mario Lucic, Sylvain Gelly, 2018, NeurIPS.

Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (2008) Achieving Master Level Play in 9 × 9 Computer Go

David Silver, Sylvain Gelly, D. Silver, 2022 .

Critical Hyper-Parameters: No Random, No Cry pdf

Olivier Teytaud, Sylvain Gelly, Olivier Bousquet, 2017, ArXiv.

The Visual Task Adaptation Benchmark pdf

Xiaohua Zhai, Lucas Beyer, Alexander Kolesnikov, 2019, ArXiv.

Combiner connaissances expertes, hors-ligne, transientes et en ligne pour l'exploration Monte-Carlo. Apprentissage et MC

Olivier Teytaud, Christophe Fiter, Julien Perez, 2009, Rev. d'Intelligence Artif..

TD Learning with Neural Networks - Study of the Leakage Propagation Problem

Timothy A. Mann, Sylvain Gelly, Damien Vincent, 2018 .

Statistical asymptotic and non-asymptotic consistency of bayesian networks: convergence to the right structure and consistent probability estimates

Olivier Teytaud, Sylvain Gelly, 2005, CAP.

What Do Neural Networks Learn When Trained With Random Labels? pdf

Daniel Keysers, Olivier Bousquet, Sylvain Gelly, 2020, NeurIPS.

MOGO WINS 19x19 GO TOURNAMENT

Sylvain Gelly, Yizao Wang, 2007 .

Online Hyper-Parameter Optimization

Nicolas Le Roux, Sylvain Gelly, Olivier Bousquet, 2018 .

Resource-Aware Parameterizations of EDA

Christian Gagné, Olivier Teytaud, Sylvain Gelly, 2006, 2006 IEEE International Conference on Evolutionary Computation.

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates

Carlos Riquelme, Gergely Neu, Sylvain Gelly, 2019, NeurIPS.

On the Parallelization of Monte-Carlo planning

Olivier Teytaud, Sylvain Gelly, Arpad Rimmel, 2008, ICINCO 2008.

MemGEN: Memory is All You Need pdf

Xiaohua Zhai, Sylvain Gelly, Karol Kurach, 2018, ArXiv.

Combining online and offline knowledge in UCT

David Silver, Sylvain Gelly, D. Silver, 2007, ICML '07.

Scalable Transfer Learning with Expert Models pdf

Joan Puigcerver, Neil Houlsby, Daniel Keysers, 2020, ICLR.

High-Fidelity Image Generation With Fewer Labels pdf

Xiaohua Zhai, Olivier Bachem, Michael Tschannen, 2019, ICML.

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations pdf

Bernhard Schölkopf, Francesco Locatello, Olivier Bachem, 2018, ICML.

Semantic Bottleneck Scene Generation pdf

Trevor Darrell, Michael Tschannen, Mario Lucic, 2019, ArXiv.

Exploration exploitation in Go: UCT for Monte-Carlo Go

Sylvain Gelly, Yizao Wang, S. Gelly, 2006, NIPS 2006.

The Parallelization of Monte-Carlo Planning - Parallelization of MC-Planning

Olivier Teytaud, Sylvain Gelly, Arpad Rimmel, 2008, ICINCO-ICSO.

Temporal Difference Learning with Neural Networks - Study of the Leakage Propagation Problem pdf

Timothy A. Mann, Sylvain Gelly, André Barreto, 2018, ArXiv.

Big Transfer (BiT): General Visual Representation Learning

Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, 2020, ECCV.

What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study

Matthieu Geist, Olivier Pietquin, Raphaël Marinier, 2021, ICLR.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale pdf

Georg Heigold, Xiaohua Zhai, Lucas Beyer, 2021, ICLR.

Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark pdf

Xiaohua Zhai, Hugo Larochelle, Neil Houlsby, 2021, ArXiv.

SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size pdf

Alexander Kolesnikov, Xiaohua Zhai, Lucas Beyer, 2021, ArXiv.

Universal Consistency and Bloat in GP Some theoretical considerations about Genetic Programming from a Statistical Learning Theory viewpoint

Olivier Teytaud, Marc Schoenauer, Nicolas Bredeche, 2006, Rev. d'Intelligence Artif..