Applied Mathematics Seminar——Wasserstein-regularized learning via neural transport maps: from gradient flow to minimax
报告人：Xiuyuan Cheng (Duke University)
时间：2026-07-09 10:30-11:30
地点：智华楼-四元厅-225
Abstract:
Wasserstein regularization has become a common tool in learning problems over distributions, while its practical computation remains challenging, especially in high dimensions. This talk presents a framework for Wasserstein-regularized learning based on directly parameterizing transport maps with neural networks. Rather than working with dual potentials or entropic relaxations, we explicitly model the transport map, which enables principled optimization in Wasserstein space as well as scalable out-of-sample evaluation. One example is the implementation of Wasserstein-2 proximal steps via flow networks that realize the Jordan–Kinderlehrer–Otto (JKO) scheme, yielding a variational interpretation of flow-based generative models. The talk will also discuss a minimax regime motivated by distributionally robust optimization (DRO), where transport is chosen adversarially. In this setting, neural transport maps provide a practical framework for studying Wasserstein minimax problems and representing worst-case distributions. Together, these examples highlight the flexibility of transport-map formulations for incorporating Wasserstein geometry into learning problems over distributions.
