|
Sliced optimal transport plans with an application to conditional flow matching| title | Sliced optimal transport plans with an application to conditional flow matching |
|---|
| start_date | 2025/11/04 |
|---|
| schedule | 16h |
|---|
| online | no |
|---|
| location_info | salle Maryam Mirzakhani (bât. Borel) |
|---|
| summary | Optimal Transport (OT) has emerged as a fundamental tool in modern machine learning, mainly due to its ability to provide meaningful comparisons between probability distributions. One of the key strengths of OT is its dual nature: it not only introduces a mathematically rigorous framework defining Wasserstein distances but also constructs an optimal coupling (or transport plan) between distributions. This coupling reveals explicit correspondences between samples, enabling a broad spectrum of applications. Despite the numerous successes of optimal transport in machine learning and the availability of many tools to approximate Wasserstein distances, computing OT plans remains computationally challenging. In this talk, I will present a new methodology to efficiently approximate sliced OT plans. The formulation can be recast as a bilevel optimization problem, and I will propose a differentiable generalized approximation that can be further adapted to data residing on manifolds. Finally, I will demonstrate the practical value of this approach by introducing a novel sliced OT-based conditional flow matching method for image generation, an application where fast computation of transport plans is crucial. |
|---|
| responsibles | Leclaire |
|---|
Workflow history| from state (1) | to state | comment | date |
|---|
| submitted | published | | 2025/10/22 13:17 UTC |
| |
|