返回
Semidual Regularized Optimal Transport
DOI:10.1137/18M1208654.png)
摘要
En 中文
Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an exemplar measure out of various probability measures, as in the Wasserstein barycenter problem, or to carry out parametric inference and density fitting, where the loss is measured in terms of an optimal transport cost to the measure of observations. Despite being conceptually simple, such problems are computationally challenging because they involve minimizing over quantities (Wasserstein distances) that are themselves hard to compute. Entropic regularization has recently emerged as an efficient tool to approximate the solution of such variational Wasserstein problems. In this paper, we give a thorough duality tour of these regularization techniques. In particular, we show how important concepts from classical OT such as c-transforms and semidiscrete approaches translate into similar ideas in a regularized setting. These dual formulations lead to smooth variational problems, which can be solved using smooth, differentiable, and convex optimization problems that are simpler to implement and numerically more stable than their unregularized counterparts. We illustrate the versatility of this approach by applying it to the computation of Wasserstein barycenters and gradient flows of spatial regularization functionals.
Keyword:
optimal transport
Wasserstein barycenter
Sinkhorn algorithm
entropic regularization
gradient flows
convex optimization
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.1
论文数:
888
被引数:
1.2W
机构
引用论文
High thermal stability 3, 6-fluorene-carbazole-dendrimers as host materials for efficient solution-processed blue phosphorescent devices
Tetrahedron
IF0
Potentiometric stripping determination of mercury(II), selenium(IV), copper(II) and lead(II) at a gold film electrode in water samples电位溶出法测定水样中金膜电极上的汞 (II),硒 (IV),铜 (II) 和铅 (II)
Graphene/Ionic Liquid Binary Electrode Material for High Performance Supercapacitor用于高性能超级电容器的石墨烯/离子液体二元电极材料

