
Information matrices and generalization
This work revisits the use of information criteria to characterize the g...
read it

Reducing the variance in online optimization by transporting past gradients
Most stochastic optimization methods use gradients once before discardin...
read it

Anytime Tail Averaging
Tail averaging consists in averaging the last examples in a stream. Comm...
read it

Distributional reinforcement learning with linear function approximation
Despite many algorithmic advances, our theoretical understanding of prac...
read it

Negative eigenvalues of the Hessian in deep neural networks
The loss function of deep networks is known to be nonconvex but the pre...
read it

A Geometric Perspective on Optimal Representations for Reinforcement Learning
This paper proposes a new approach to representation learning based on g...
read it

The Value Function Polytope in Reinforcement Learning
We establish geometric and topological properties of the space of value ...
read it

Understanding the impact of entropy on policy optimization
Entropy regularization is commonly used to improve policy optimization i...
read it

Understanding the impact of entropy in policy learning
Entropy regularization is commonly used to improve policy optimization i...
read it

Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods
Our goal is to improve variance reducing stochastic methods through bett...
read it

A comparative study of counterfactual estimators
We provide a comparative study of several widely used offpolicy estimat...
read it

Efficient iterative policy optimization
We tackle the issue of finding a good policy when the number of policy u...
read it

Tighter bounds lead to improved classifiers
The standard approach to supervised classification involves the minimiza...
read it

Minimizing Finite Sums with the Stochastic Average Gradient
We propose the stochastic average gradient (SAG) method for optimizing t...
read it

Weakly Supervised Learning of ForegroundBackground Segmentation using Masked RBMs
We propose an extension of the Restricted Boltzmann Machine (RBM) that a...
read it
Nicolas Le Roux
is this you? claim profile