Date/Time
24 May 2026 - 29 May 2026

Organized by
Niao He (ETH Zurich), Yifan Hu (EPFL), Daniel Kuhn (EPFL), Jia-Jie Zhu (WIAS Berlin)

Event page & registration
https://indico.global/event/13896/

Description

In recent years, optimal transport (OT) theory has emerged as a immensely popular intersection of mathematics, statistics, and computer science, overlapping with topics including partial differential equations (PDEs), optimization, image processing, inverse problems, sampling and machine learning. The deep theoretical foundations of optimal transport have led to its critical role in addressing both classical and modern mathematical challenges. Historically, the development of OT theory has always been intertwined with the advances in computational mathematics and optimization theory. However, in the recent years, the specific fields have been evolving separately, and the interactions between researchers have become less frequent. This workshop will bring together
researchers from diverse fields, with a primary focus on advancing the theoretical aspects of optimal transport and exploring its intricate connections to bleeding-edge applications such as deep generative models based on flows, domain adaptation, and data-driven robust optimization and training of deep models. Our goal is to bring together leading researchers and early-career scholars from these two communities to foster interdisciplinary dialogue and collaboration.

Schedule

Location
SwissMAP Research Station, Les Diablerets, Switzerland