Yann Ollivier

According to our database, Yann Ollivier authored at least 38 papers between 2003 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Simple Ingredients for Offline Reinforcement Learning.

Edoardo Cetin, Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric, Yann Ollivier, Ahmed Touati

CoRR, 2024

2023

Does Zero-Shot Reinforcement Learning Exist?

Ahmed Touati, Jérémy Rapin, Yann Ollivier

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Agnostic Physics-Driven Deep Learning.

Benjamin Scellier, Siddhartha Mishra, Yoshua Bengio, Yann Ollivier

CoRR, 2022

2021

Unbiased Methods for Multi-Goal Reinforcement Learning.

Léonard Blier, Yann Ollivier

CoRR, 2021

Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint.

Léonard Blier, Corentin Tallec, Yann Ollivier

CoRR, 2021

Learning One Representation to Optimize All Rewards.

Ahmed Touati, Yann Ollivier

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Interpreting a Penalty as the Influence of a Bayesian Prior.

Pierre Wolinski, Guillaume Charpiat, Yann Ollivier

CoRR, 2020

2019

Separating value functions across time-scales.

Joshua Romoff, Peter Henderson, Ahmed Touati, Yann Ollivier, Emma Brunskill, Joelle Pineau

CoRR, 2019

Learning with Random Learning Rates.

Léonard Blier, Pierre Wolinski, Yann Ollivier

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2019

Making Deep Q-learning methods robust to time discretization.

Corentin Tallec, Léonard Blier, Yann Ollivier

Proceedings of the 36th International Conference on Machine Learning, 2019

First-Order Adversarial Vulnerability of Neural Networks and Input Dimension.

Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz

Proceedings of the 36th International Conference on Machine Learning, 2019

White-box vs Black-box: Bayes Optimal Strategies for Membership Inference.

Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Yann Ollivier, Hervé Jégou

Proceedings of the 36th International Conference on Machine Learning, 2019

Separable value functions across time-scales.

Joshua Romoff, Peter Henderson, Ahmed Touati, Yann Ollivier, Joelle Pineau, Emma Brunskill

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies.

Yann Ollivier

CoRR, 2018

Do Deep Learning Models Have Too Many Parameters? An Information Theory Viewpoint.

Léonard Blier, Yann Ollivier

CoRR, 2018

Adversarial Vulnerability of Neural Networks Increases With Input Dimension.

Carl-Johann Simon-Gabriel, Yann Ollivier, Bernhard Schölkopf, Léon Bottou, David Lopez-Paz

CoRR, 2018

The Description Length of Deep Learning models.

Léonard Blier, Yann Ollivier

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Mixed batches and symmetric discriminators for GAN training.

Thomas Lucas, Corentin Tallec, Yann Ollivier, Jakob Verbeek

Proceedings of the 35th International Conference on Machine Learning, 2018

Can recurrent neural networks warp time?

Corentin Tallec, Yann Ollivier

Proceedings of the 6th International Conference on Learning Representations, 2018

Unbiased Online Recurrent Optimization.

Corentin Tallec, Yann Ollivier

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles.

Yann Ollivier, Ludovic Arnold, Anne Auger, Nikolaus Hansen

J. Mach. Learn. Res., 2017

True Asymptotic Natural Gradient Optimization.

Yann Ollivier

CoRR, 2017

Unbiasing Truncated Backpropagation Through Time.

Corentin Tallec, Yann Ollivier

CoRR, 2017

Natural Langevin Dynamics for Neural Networks.

Gaétan Marceau-Caron, Yann Ollivier

Proceedings of the Geometric Science of Information - Third International Conference, 2017

2016

Practical Riemannian Neural Networks.

Gaétan Marceau-Caron, Yann Ollivier

CoRR, 2016

2015

Training recurrent networks online without backtracking.

Yann Ollivier, Guillaume Charpiat

CoRR, 2015

Speed learning on the fly.

Pierre-Yves Massé, Yann Ollivier

CoRR, 2015

Laplace's Rule of Succession in Information Geometry.

Yann Ollivier

Proceedings of the Geometric Science of Information - Second International Conference, 2015

2014

Auto-encoders: reconstruction versus compression.

Yann Ollivier

CoRR, 2014

2013

Riemannian metrics for neural networks

Yann Ollivier

CoRR, 2013

Persistent Contextual Neural Networks for learning symbolic data sequences.

Yann Ollivier

CoRR, 2013

Information-Geometric Optimization: The Interest of Information Theory for Discrete and Continuous Optimization.

Yann Ollivier

Proceedings of the Geometric Science of Information - First International Conference, 2013

Objective improvement in information-geometric optimization.

Youhei Akimoto, Yann Ollivier

Proceedings of the Foundations of Genetic Algorithms XII, 2013

2012

A Curved Brunn-Minkowski Inequality on the Discrete Hypercube, Or: What Is the Ricci Curvature of the Discrete Hypercube?

Yann Ollivier, Cédric Villani

SIAM J. Discret. Math., 2012

Layer-wise learning of deep generative models

Ludovic Arnold, Yann Ollivier

CoRR, 2012

2007

Some Small Cancellation Properties of Random Groups.

Yann Ollivier

Int. J. Algebra Comput., 2007

Finding Related Pages Using Green Measures: An Illustration with Wikipedia.

Yann Ollivier, Pierre Senellart

Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, 2007

2003

Rate of convergence of crossover operators.

Yann Ollivier

Random Struct. Algorithms, 2003