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

- Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport

  • Authors: F. Genans, A. Godichon-Baggioni, F-X Vialard, O; Wintenberger
  • Short abstract: We introduce DRAG, a stochastic algorithm for semi-discrete Optimal Transport that decreases entropic regularization during training. This yields unbiased estimates and faster convergence than fixed-regularization methods, with both theory and experiments confirming its efficiency.
  • Link: Soon available, paper under review.

- Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate

  • Authors: F. Genans, A. Godichon-Baggioni, F-X Vialard, O; Wintenberger
  • Short abstract: We prove that Stochastic Gradient Descent can efficiently approximate the OT map in the semi-discrete setting, even in an online fashion, establishing the first minimax convergence guarantees for a broad class of cost functions and non-compact measures.
  • Link: Soon available, paper under review.