← Search

Naoya Yamamoto

1 accepted papers

2025

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points

NeurIPS 2025poster

Wasserstein gradient flow (WGF) is a common method to perform optimization over the space of probability measures. While WGF is guaranteed to converge to a first-order stationary point, for nonconvex functionals the converged solution does not necessarily satisfy the second-order optimality conditio…

Cited by 0SourceScholar