English

Forward-Euler time-discretization for Wasserstein gradient flows can be wrong

Machine Learning 2024-06-13 v1 Machine Learning Optimization and Control

Abstract

In this note, we examine the forward-Euler discretization for simulating Wasserstein gradient flows. We provide two counter-examples showcasing the failure of this discretization even for a simple case where the energy functional is defined as the KL divergence against some nicely structured probability densities. A simple explanation of this failure is also discussed.

Cite

@article{arxiv.2406.08209,
  title  = {Forward-Euler time-discretization for Wasserstein gradient flows can be wrong},
  author = {Yewei Xu and Qin Li},
  journal= {arXiv preprint arXiv:2406.08209},
  year   = {2024}
}
R2 v1 2026-06-28T17:03:06.544Z