AIConfPaper
← Search

Ferdinand Genans

2 accepted papers

2025

Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport

Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard, Olivier Wintenberger
NeurIPS 2025poster

Adding entropic regularization to Optimal Transport (OT) problems has become a standard approach for designing efficient and scalable solvers. However, regularization introduces a bias from the true solution. To mitigate this bias while still benefiting from the acceleration provided by regularizati…

Cited by 0Source ↗Scholar ↗
2025

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

Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard, Olivier Wintenberger
NeurIPS 2025spotlight

We investigate the semi-discrete Optimal Transport (OT) problem, where a continuous source measure $\mu$ is transported to a discrete target measure $\nu$, with particular attention to the OT map approximation. In this setting, Stochastic Gradient Descent (SGD) based solvers have demonstrated strong…

Cited by 0Source ↗Scholar ↗