My research focuses on optimal transport problems and their link with subfields of optimization, such as stochastic, online, and convex optimization. The goal is to design efficient algorithms with the best computational and statistical complexity.

Recent Publications/Preprints

- Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization

• Authors: F. Genans, A. Godichon-Baggioni, F-X Vialard, O; Wintenberger
• Short abstract: In the semi-discrete Optimal Transport (OT) setting, where the source measure is continuous and the target is discrete, we prove that estimating the OT cost and OT map with the usual quadratic cost is a non-regular parametric problem. This means it benefits from enhanced convergence rates. Moreover, we design a gradient-based algorithm with decreasing entropy regularization to nearly match the lower bounds we proved.
• Link: ArXiv