b'Yann Ollivier'

research

∙ 09/29/2022

Does Zero-Shot Reinforcement Learning Exist?

A zero-shot RL agent is an agent that can solve any RL task in a given e...

6 Ahmed Touati, et al. ∙

research

∙ 05/30/2022

Agnostic Physics-Driven Deep Learning

This work establishes that a physical system can perform statistical lea...

0 Benjamin Scellier, et al. ∙

research

∙ 06/16/2021

Unbiased Methods for Multi-Goal Reinforcement Learning

In multi-goal reinforcement learning (RL) settings, the reward for each ...

0 Léonard Blier, et al. ∙

research

∙ 03/14/2021

Learning One Representation to Optimize All Rewards

We introduce the forward-backward (FB) representation of the dynamics of...

8 Ahmed Touati, et al. ∙

research

∙ 01/18/2021

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

In reinforcement learning, temporal difference-based algorithms can be s...

0 Léonard Blier, et al. ∙

research

∙ 05/12/2020

Convergence of Online Adaptive and Recurrent Optimization Algorithms

We prove local convergence of several notable gradient descentalgorithms...

0 Pierre-Yves Massé, et al. ∙

research

∙ 02/01/2020

Interpreting a Penalty as the Influence of a Bayesian Prior

In machine learning, it is common to optimize the parameters of a probab...

0 Pierre Wolinski, et al. ∙

research

∙ 08/29/2019

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

Membership inference determines, given a sample and trained parameters o...

12 Alexandre Sablayrolles, et al. ∙

research

∙ 02/05/2019

Separating value functions across time-scales

In many finite horizon episodic reinforcement learning (RL) settings, it...

0 Joshua Romoff, et al. ∙

research

∙ 01/28/2019

Making Deep Q-learning methods robust to time discretization

Despite remarkable successes, Deep Reinforcement Learning (DRL) is not r...

14 Corentin Tallec, et al. ∙

research

∙ 01/03/2019

The Extended Kalman Filter is a Natural Gradient Descent in Trajectory Space

The extended Kalman filter is perhaps the most standard tool to estimate...

0 Yann Ollivier, et al. ∙

research

∙ 10/02/2018

Learning with Random Learning Rates

Hyperparameter tuning is a bothersome step in the training of deep learn...

32 Léonard Blier, et al. ∙

research

∙ 06/19/2018

Mixed batches and symmetric discriminators for GAN training

Generative adversarial networks (GANs) are pow- erful generative models ...

0 Thomas Lucas, et al. ∙

research

∙ 05/02/2018

Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies

In reinforcement learning, temporal difference (TD) is the most direct a...

0 Yann Ollivier, et al. ∙

research

∙ 03/23/2018

Can recurrent neural networks warp time?

Successful recurrent models such as long short-term memories (LSTMs) and...

0 Corentin Tallec, et al. ∙

research

∙ 02/20/2018

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

Deep learning models often have more parameters than observations, and s...

0 Léonard Blier, et al. ∙

research

∙ 02/05/2018

Adversarial Vulnerability of Neural Networks Increases With Input Dimension

Over the past four years, neural networks have proven vulnerable to adve...

0 Carl-Johann Simon-Gabriel, et al. ∙

research

∙ 12/22/2017

True Asymptotic Natural Gradient Optimization

We introduce a simple algorithm, True Asymptotic Natural Gradient Optimi...

0 Yann Ollivier, et al. ∙

research

∙ 12/04/2017

Natural Langevin Dynamics for Neural Networks

One way to avoid overfitting in machine learning is to use model paramet...

0 Gaétan Marceau-Caron, et al. ∙

research

∙ 05/23/2017

Unbiasing Truncated Backpropagation Through Time

Truncated Backpropagation Through Time (truncated BPTT) is a widespread ...

0 Corentin Tallec, et al. ∙

research

∙ 03/01/2017

Online Natural Gradient as a Kalman Filter

We establish a full relationship between Kalman filtering and Amari's na...

0 Yann Ollivier, et al. ∙

research

∙ 02/16/2017

Unbiased Online Recurrent Optimization

The novel Unbiased Online Recurrent Optimization (UORO) algorithm allows...

0 Corentin Tallec, et al. ∙

research

∙ 02/25/2016

Practical Riemannian Neural Networks

We provide the first experimental results on non-synthetic datasets for ...

0 Gaétan Marceau-Caron, et al. ∙

research

∙ 11/08/2015

Speed learning on the fly

The practical performance of online stochastic gradient descent algorith...

0 Pierre-Yves Massé, et al. ∙

research

∙ 07/28/2015

Training recurrent networks online without backtracking

We introduce the "NoBackTrack" algorithm to train the parameters of dyna...

0 Yann Ollivier, et al. ∙

research

∙ 03/30/2014

Auto-encoders: reconstruction versus compression

We discuss the similarities and differences between training an auto-enc...

0 Yann Ollivier, et al. ∙

research

∙ 06/03/2013

Riemannian metrics for neural networks II: recurrent networks and learning symbolic data sequences

Recurrent neural networks are powerful models for sequential data, able ...

0 Yann Ollivier, et al. ∙

research

∙ 03/04/2013

Riemannian metrics for neural networks I: feedforward networks

We describe four algorithms for neural network training, each adapted to...

0 Yann Ollivier, et al. ∙

research

∙ 12/07/2012

Layer-wise learning of deep generative models

When using deep, multi-layered architectures to build generative models ...

0 Ludovic Arnold, et al. ∙

research

∙ 11/16/2012

Objective Improvement in Information-Geometric Optimization

Information-Geometric Optimization (IGO) is a unified framework of stoch...

0 Youhei Akimoto, et al. ∙

Yann Ollivier

Featured Co-authors