Efficient Gradient Flows in Sliced-Wasserstein Space

arXiv2110.10972MaRDI QIDQ6380916FDOQ6380916

Authors: Clément Bonet, Nicolas Courty, François Septier, Lucas Drumetz 

Publication date: 21 October 2021

Abstract: Minimizing functionals in the space of probability distributions can be done with Wasserstein gradient flows. To solve them numerically, a possible approach is to rely on the Jordan-Kinderlehrer-Otto (JKO) scheme which is analogous to the proximal scheme in Euclidean spaces. However, it requires solving a nested optimization problem at each iteration, and is known for its computational challenges, especially in high dimension. To alleviate it, very recent works propose to approximate the JKO scheme leveraging Brenier's theorem, and using gradients of Input Convex Neural Networks to parameterize the density (JKO-ICNN). However, this method comes with a high computational cost and stability issues. Instead, this work proposes to use gradient flows in the space of probability measures endowed with the sliced-Wasserstein (SW) distance. We argue that this method is more flexible than JKO-ICNN, since SW enjoys a closed-form differentiable approximation. Thus, the density at each step can be parameterized by any generative model which alleviates the computational burden and makes it tractable in higher dimensions.

Has companion code repository: https://github.com/clbonet/Sliced-Wasserstein_Gradient_Flows

This page was built for publication: Efficient Gradient Flows in Sliced-Wasserstein Space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6380916)