Publications by Lénaïc Chizat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We consider the problem of computing mixed Nash equilibria of two-player zero-sum games with continuous sets of pure strategies and with first-order access to the payoff function. This problem arises for example in game-theory-inspired machine learning app ...

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for infinite-width 2- ...

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a general class of s ...

We study the convergence rate of Sinkhorn's algorithm for solving entropy-regularized optimal transport problems when at least one of the probability measures, mu, admits a density over R-d. For a semi-concave cost function bounded by cand a regularization ...

The function that maps a family of probability measures to the solution of the dual entropic optimal transport problem is known as the Schr center dot odinger map. We prove that when the cost function is Ck+1 with k is an element of N* then this map is Lip ...

This paper studies the infinite-width limit of deep linear neural networks (NNs) initialized with random parameters. We obtain that, when the number of parameters diverges, the training dynamics converge (in a precise sense) to the dynamics obtained from a ...

We study a general formulation of regularized Wasserstein barycenters that enjoy favorable regularity, approximation, stability and (grid-free) optimization properties. This barycenter is defined as the unique probability measure that minimizes the sum of ...

Lénaïc Chizat

Chat with Graph Search

An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

On the symmetries in the dynamics of wide two-layer neural networks

Sharper Exponential Convergence Rates for Sinkhorn's Algorithm in Continuous Settings

Displacement smoothness of entropic optimal transport

Infinite-width limit of deep linear neural networks

Doubly Regularized Entropic Wasserstein Barycenter