中文
相关论文

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

200 篇论文

We consider Monge-Kantorovich optimal transport problems on $\mathbb{R}^d$, $d\ge 1$, with a convex cost function given by the cumulant generating function of a probability measure. Examples include the Wasserstein-2 transport whose cost…

概率论 · 数学 2017-08-29 Soumik Pal

We propose a distributed nonparametric algorithm for solving measure-valued optimization problems with additive objectives. Such problems arise in several contexts in stochastic learning and control including Langevin sampling from an…

最优化与控制 · 数学 2022-02-21 Iman Nodozi , Abhishek Halder

This paper presents a Wasserstein attraction approach for solving dynamic mass transport problems over networks. In the transport problem over networks, we start with a distribution over the set of nodes that needs to be "transported" to a…

最优化与控制 · 数学 2022-04-28 Ferran Arqué , César A. Uribe , Carlos Ocampo-Martinez

This paper exploit the equivalence between the Schr\"odinger Bridge problem and the entropy penalized optimal transport in order to find a different approach to the duality, in the spirit of optimal transport. This approach results in a…

概率论 · 数学 2019-11-19 Simone Di Marino , Augusto Gerolin

Many problems in machine learning can be formulated as solving entropy-regularized optimal transport on the space of probability measures. The canonical approach involves the Sinkhorn iterates, renowned for their rich mathematical…

机器学习 · 计算机科学 2023-11-29 Mohammad Reza Karimi , Ya-Ping Hsieh , Andreas Krause

By adding entropic regularization, multi-marginal optimal transport problems can be transformed into tensor scaling problems, which can be solved numerically using the multi-marginal Sinkhorn algorithm. The main computational bottleneck of…

数值分析 · 数学 2023-02-07 Christoph Strössner , Daniel Kressner

Inspired by the matching of supply to demand in logistical problems, the optimal transport (or Monge--Kantorovich) problem involves the matching of probability distributions defined over a geometric domain such as a surface or manifold. In…

最优化与控制 · 数学 2018-05-02 Justin Solomon

Optimal transport is a notoriously difficult problem to solve numerically, with current approaches often remaining intractable for very large scale applications such as those encountered in machine learning. Wasserstein barycenters -- the…

机器学习 · 计算机科学 2021-02-25 Julien Lacombe , Julie Digne , Nicolas Courty , Nicolas Bonneel

Optimal transportation distances are a fundamental family of parameterized distances for histograms. Despite their appealing theoretical properties, excellent performance in retrieval tasks and intuitive formulation, their computation…

机器学习 · 统计学 2014-03-25 Marco Cuturi

This article details a novel numerical scheme to approximate gradient flows for optimal transport (i.e. Wasserstein) metrics. These flows have proved useful to tackle theoretically and numerically non-linear diffusion equations that model…

最优化与控制 · 数学 2015-03-10 Gabriel Peyré

Optimal transport (OT) plays an essential role in various areas like machine learning and deep learning. However, computing discrete optimal transport plan for large scale problems with adequate accuracy and efficiency is still highly…

机器学习 · 计算机科学 2021-07-20 Dongsheng An , Na Lei , Xianfeng Gu

Entropic regularization provides a generalization of the original optimal transport problem. It introduces a penalty term defined by the Kullback-Leibler divergence, making the problem more tractable via the celebrated Sinkhorn algorithm.…

最优化与控制 · 数学 2023-01-04 Dávid Terjék , Diego González-Sánchez

The Sinkhorn algorithm is a widely used method for solving the optimal transport problem, and the Greenkhorn algorithm is one of its variants. While there are modified versions of these two algorithms whose computational complexities are…

最优化与控制 · 数学 2023-10-20 Jianzhou Luo , Dingchuan Yang , Ke Wei

The distance and divergence of the probability measures play a central role in statistics, machine learning, and many other related fields. The Wasserstein distance has received much attention in recent years because of its distinctions…

统计理论 · 数学 2021-03-11 Qijun Tong , Kei Kobayashi

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

最优化与控制 · 数学 2018-10-30 Lenaic Chizat , Francis Bach

We consider synthesis and analysis of probability measures using the entropy-regularized Wasserstein-2 cost and its unbiased version, the Sinkhorn divergence. The synthesis problem consists of computing the barycenter, with respect to these…

机器学习 · 统计学 2025-03-25 Brendan Mallery , James M. Murphy , Shuchin Aeron

This work introduces novel computational methods for entropic optimal transport (OT) problems under martingale-type conditions. The considered problems include the discrete martingale optimal transport (MOT) problem. Moreover, as the…

最优化与控制 · 数学 2025-08-26 Xun Tang , Michael Shavlovsky , Holakou Rahmanian , Tesi Xiao , Lexing Ying

We analyze two algorithms for approximating the general optimal transport (OT) distance between two discrete distributions of size $n$, up to accuracy $\varepsilon$. For the first algorithm, which is based on the celebrated Sinkhorn's…

数据结构与算法 · 计算机科学 2018-06-08 Pavel Dvurechensky , Alexander Gasnikov , Alexey Kroshnin

We show that the derivatives of the Sinkhorn-Knopp algorithm, or iterative proportional fitting procedure, converge towards the derivatives of the entropic regularization of the optimal transport problem with a locally uniform linear…

最优化与控制 · 数学 2022-08-04 Edouard Pauwels , Samuel Vaiter

Computing Wasserstein barycenters (a.k.a. Optimal Transport barycenters) is a fundamental problem in geometry which has recently attracted considerable attention due to many applications in data science. While there exist polynomial-time…

最优化与控制 · 数学 2022-02-15 Jason M. Altschuler , Enric Boix-Adsera