A Unifying View of Variational Generative Wasserstein Flows 事件

A Unifying View of Variational Generative Wasserstein Flows arXiv:2605.31369v1 Announce Type: cross Abstract: Many modern generative models can be viewed as minimizing divergences between probability distributions, yet they rely on different algorithmic and geometric principles. Wasserstein gradient flows provide a continuous-time formulation for optimizing over distributions, and can be approximated through their implicit discretization via the Jordan-Kinderlehrer-Otto (JKO) scheme. In this wo