中文
相关论文

相关论文: Deriving the Gradients of Some Popular Optimal Tra…

200 篇论文

Optimal transport (OT) provides powerful tools for comparing probability measures in various types. The Wasserstein distance which arises naturally from the idea of OT is widely used in many machine learning applications. Unfortunately,…

最优化与控制 · 数学 2021-06-03 Shu Liu , Haodong Sun , Hongyuan Zha

In this work, we develop a collection of novel methods for the entropic-regularised optimal transport problem, which are inspired by existing mirror descent interpretations of the Sinkhorn algorithm used for solving this problem. These are…

最优化与控制 · 数学 2025-07-17 Vishwak Srinivasan , Qijia Jiang

We present a novel method for efficiently computing optimal transport maps and Wasserstein barycenters in high-dimensional spaces. Our approach uses conditional normalizing flows to approximate the input distributions as invertible…

机器学习 · 统计学 2025-05-29 Gabriele Visentin , Patrick Cheridito

This chapter describes techniques for the numerical resolution of optimal transport problems. We will consider several discretizations of these problems, and we will put a strong focus on the mathematical analysis of the algorithms to solve…

数值分析 · 数学 2020-03-03 Quentin Merigot , Boris Thibert

Starting from Brenier's relaxed formulation of the incompressible Euler equation in terms of geodesics in the group of measure-preserving diffeomorphisms, we propose a numerical method based on Sinkhorn's algorithm for the entropic…

数值分析 · 数学 2018-03-06 Jean-David Benamou , Guillaume Carlier , Luca Nenna

Optimal transport (OT) distances are finding evermore applications in machine learning and computer vision, but their wide spread use in larger-scale problems is impeded by their high computational cost. In this work we develop a family of…

机器学习 · 统计学 2018-03-06 Brahim Khalil Abid , Robert M. Gower

Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications. This paper develops a scalable first-order optimization-based method that computes…

机器学习 · 计算机科学 2024-06-21 Gen Li , Yanxi Chen , Yu Huang , Yuejie Chi , H. Vincent Poor , Yuxin Chen

Computationally solving multi-marginal optimal transport (MOT) with squared Euclidean costs for $N$ discrete probability measures has recently attracted considerable attention, in part because of the correspondence of its solutions with…

数值分析 · 数学 2022-02-03 Johannes von Lindheim

This paper is devoted to the stochastic approximation of entropically regularized Wasserstein distances between two probability measures, also known as Sinkhorn divergences. The semi-dual formulation of such regularized optimal…

统计理论 · 数学 2024-12-10 Bernard Bercu , Jérémie Bigot

Wasserstein barycenters provide a geometrically meaningful way to aggregate probability distributions, built on the theory of optimal transport. They are difficult to compute in practice, however, leading previous work to restrict their…

机器学习 · 计算机科学 2020-10-27 Lingxiao Li , Aude Genevay , Mikhail Yurochkin , Justin Solomon

Given a collection of probability measures, a practitioner sometimes needs to find an "average" distribution which adequately aggregates reference distributions. A theoretically appealing notion of such an average is the Wasserstein…

The optimal transport barycenter (a.k.a. Wasserstein barycenter) is a fundamental notion of averaging that extends from the Euclidean space to the Wasserstein space of probability distributions. Computation of the unregularized barycenter…

机器学习 · 统计学 2025-05-27 Kaheon Kim , Rentian Yao , Changbo Zhu , Xiaohui Chen

Wasserstein barycentres represent average distributions between multiple probability measures for the Wasserstein distance. The numerical computation of Wasserstein barycentres is notoriously challenging. A common approach is to use…

数值分析 · 数学 2026-03-30 Eloi Tanguy , Julie Delon , Nathaël Gozlan

We study the existing algorithms that solve the multidimensional martingale optimal transport. Then we provide a new algorithm based on entropic regularization and Newton's method. Then we provide theoretical convergence rate results and we…

概率论 · 数学 2018-12-31 Hadrien De March

This article introduces a new notion of optimal transport (OT) between tensor fields, which are measures whose values are positive semidefinite (PSD) matrices. This "quantum" formulation of OT (Q-OT) corresponds to a relaxed version of the…

图形学 · 计算机科学 2017-07-25 Gabriel Peyré , Lenaïc Chizat , François-Xavier Vialard , Justin Solomon

In [Q. Liao et al., Commun. Math. Sci., 20(2022)], a linear-time Sinkhorn algorithm is developed based on dynamic programming, which significantly reduces the computational complexity involved in solving optimal transport problems. However,…

最优化与控制 · 数学 2025-03-25 Ziyuan Lyu , Zihao Wang , Hao Wu , Shuai Yang

Entropy regularization in optimal transport (OT) has been the driver of many recent interests for Wasserstein metrics and barycenters in machine learning. It allows to keep the appealing geometrical properties of the unregularized…

机器学习 · 统计学 2020-06-05 Hicham Janati , Marco Cuturi , Alexandre Gramfort

We study the problem of the decentralized computation of entropy-regularized semi-discrete Wasserstein barycenters over a network. Building upon recent primal-dual approaches, we propose a sampling gradient quantization scheme that allows…

最优化与控制 · 数学 2020-10-28 Roman Krawtschenko , César A. Uribe , Alexander Gasnikov , Pavel Dvurechensky

Solving large scale entropic optimal transport problems with the Sinkhorn algorithm remains challenging, and domain decomposition has been shown to be an efficient strategy for problems on large grids. Unbalanced optimal transport is a…

最优化与控制 · 数学 2026-01-26 Ismael Medina , The Sang Nguyen , Bernhard Schmitzer

Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal transport have been…

最优化与控制 · 数学 2023-01-18 Thibault Séjourné , Jean Feydy , François-Xavier Vialard , Alain Trouvé , Gabriel Peyré