activity
20182020
most citedQuantitative Propagation of Chaos for SGD in Wide Neural Networks

13 citations · 13 across the 1 of their papers we have counts for

collaborators

5 papers

stat.ML202013 cited

Quantitative Propagation of Chaos for SGD in Wide Neural Networks

Valentin De Bortoli, Alain Durmus, Xavier Fontaine +1

In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neura…

math.OC2020

Convergence rates and approximation results for SGD and its continuous-time counterpart

Xavier Fontaine, Valentin De Bortoli, Alain Durmus

This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD) with non-increasing step sizes. First, we show that the recursion defining SGD can be prova…

stat.ML2019

Online A-Optimal Design and Active Linear Regression

Xavier Fontaine, Pierre Perrault, Michal Valko +1

We consider in this paper the problem of optimal experiment design where a decision maker can choose which points to sample to obtain an estimate of the hidden parameter $β…

stat.ML2019

An adaptive stochastic optimization algorithm for resource allocation

Xavier Fontaine, Shie Mannor, Vianney Perchet

We consider the classical problem of sequential resource allocation where a decision maker must repeatedly divide a budget between several resources, each with diminishing returns.…

stat.ML2018

Regularized Contextual Bandits

Xavier Fontaine, Quentin Berthet, Vianney Perchet

We consider the stochastic contextual bandit problem with additional regularization. The motivation comes from problems where the policy of the agent must be close to some baseline…