Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization
Keywords: wasserstein-2 barycenters, non-minimax optimization, cycle-consistency regularizer, input convex neural networks, continuous case
Abstract: Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport. In this paper, we present a scalable algorithm to compute Wasserstein-2 barycenters given sample access to the input measures, which are not restricted to being discrete. While past approaches rely on entropic or quadratic regularization, we employ input convex neural networks and cycle-consistency regularization to avoid introducing bias. As a result, our approach does not resort to minimax optimization. We provide theoretical analysis on error bounds as well as empirical evidence of the effectiveness of the proposed approach in low-dimensional qualitative scenarios and high-dimensional quantitative experiments.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
One-sentence Summary: We present a new algorithm to compute Wasserstein-2 barycenters of continuous distributions powered by a straightforward optimization procedure without introducing bias or a generative model.
Supplementary Material: zip
Code: [ 2 community implementations](https://paperswithcode.com/paper/?openreview=3tFAs5E-Pe)
13 Replies
Loading