Wasserstein Iterative Networks for Barycenter Estimation

NeurIPS 2022(2022)

引用 18|浏览6
暂无评分
摘要
Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way. In this paper, we present an algorithm to approximate the Wasserstein-2 barycenters of continuous measures via a generative model. Previous approaches rely on regularization (entropic/quadratic) which introduces bias or on input convex neural networks which are not expressive enough for large-scale tasks. In contrast, our algorithm does not introduce bias and allows using arbitrary neural networks. In addition, based on the celebrity faces dataset, we construct Ave, celeba! dataset which can be used for quantitative evaluation of barycenter algorithms by using standard metrics of generative models such as FID.
更多
查看译文
关键词
optimal transport,continuous barycenter,neural networks,Wasserstein-2 distance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络