中文
相关论文

相关论文: Thermodynamic structure of the Sinkhorn flow

200 篇论文

In this paper, we are motivated by two important applications: entropy-regularized optimal transport problem and road or IP traffic demand matrix estimation by entropy model. Both of them include solving a special type of optimization…

最优化与控制 · 数学 2017-09-27 Pavel Dvurechensky , Alexander Gasnikov , Sergey Omelchenko , Alexander Tiurin

The function that maps a family of probability measures to the solution of the dual entropic optimal transport problem is known as the Schr\"odinger map. We prove that when the cost function is $\mathcal{C}^{k+1}$ with $k\in \mathbb{N}^*$…

最优化与控制 · 数学 2024-03-04 Guillaume Carlier , Lénaïc Chizat , Maxime Laborde

In the early 1930's, Erwin Schroedinger, motivated by his quest for a more classical formulation of quantum mechanics, posed a large deviation problem for a cloud of independent Brownian particles. He showed that the solution to the problem…

最优化与控制 · 数学 2018-09-21 Montacer Essid , Michele Pavon

Mass transport problems arise in many areas of machine learning whereby one wants to compute a map transporting one distribution to another. Generative modeling techniques like Generative Adversarial Networks (GANs) and Denoising Diffusion…

机器学习 · 计算机科学 2024-09-17 Valentin De Bortoli , Iryna Korshunova , Andriy Mnih , Arnaud Doucet

We propose the Entropic-regularized Robust Optimal Transport (E-ROBOT) framework, a novel method that combines the robustness of ROBOT with the computational and statistical benefits of entropic regularization. We show that, rooted in the…

机器学习 · 统计学 2025-09-16 Davide La Vecchia , Hang Liu

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

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

机器学习 · 统计学 2019-06-04 Giulia Luise , Alessandro Rudi , Massimiliano Pontil , Carlo Ciliberto

We study Sinkhorn's algorithm for solving the entropically regularized optimal transport problem. Its iterate $\pi_{t}$ is shown to satisfy $H(\pi_{t}|\pi_{*})+H(\pi_{*}|\pi_{t})=O(t^{-1})$ where $H$ denotes relative entropy and $\pi_{*}$…

最优化与控制 · 数学 2025-04-08 Promit Ghosal , Marcel Nutz

Entropy regularized optimal transport and its multi-marginal generalization have attracted increasing attention in various applications, in particular due to efficient Sinkhorn-like algorithms for computing optimal transport plans. However,…

最优化与控制 · 数学 2023-01-25 Florian Beier , Johannes von Lindheim , Sebastian Neumayer , Gabriele Steidl

The Schr\"{o}dinger Bridge Problem (SBP), which can be understood as an entropy-regularized optimal transport, seeks to compute stochastic dynamic mappings connecting two given distributions. SBP has shown significant theoretical importance…

最优化与控制 · 数学 2025-03-25 Yang Jing , Lei Li , Jingtong Zhang

We study stability of optimizers and convergence of Sinkhorn's algorithm for the entropic optimal transport problem. In the special case of the quadratic cost, our stability bounds imply that if one of the two entropic potentials is…

概率论 · 数学 2025-10-06 Alberto Chiarini , Giovanni Conforti , Giacomo Greco , Luca Tamanini

This survey has been written in occasion of the School and Workshop about Optimal Transport on Quantum Structures at Erd\"os Center in September 2022. We discuss some recent results on noncommutative entropic optimal transport problems and…

数学物理 · 物理学 2023-10-17 Lorenzo Portinale

The Entropic Optimal Transport (EOT) problem and its dynamic counterpart, the Schr\"odinger bridge (SB) problem, play an important role in modern machine learning, linking generative modeling with optimal transport theory. While recent…

The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (potential energy). These combinations yield different…

机器学习 · 计算机科学 2024-07-04 Kirill Neklyudov , Rob Brekelmans , Alexander Tong , Lazar Atanackovic , Qiang Liu , Alireza Makhzani

We establish the stability of solutions to the entropically regularized optimal transport problem with respect to the marginals and the cost function. The result is based on the geometric notion of cyclical invariance and inspired by the…

最优化与控制 · 数学 2022-07-07 Promit Ghosal , Marcel Nutz , Espen Bernton

Monge-Kantorovich optimal mass transport (OMT) provides a blueprint for geometries in the space of positive densities -- it quantifies the cost of transporting a mass distribution into another. In particular, it provides natural options for…

最优化与控制 · 数学 2015-06-16 Yongxin Chen , Tryphon T. Georgiou , Michele Pavon

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

Diffusion models have become the go-to method for large-scale generative models in real-world applications. These applications often involve data distributions confined within bounded domains, typically requiring ad-hoc thresholding…

机器学习 · 统计学 2024-01-09 Wei Deng , Yu Chen , Nicole Tianjiao Yang , Hengrong Du , Qi Feng , Ricky T. Q. Chen

In this note, I review entropy-regularized Monge-Kantorovich problem in Optimal Transport, and derive the gradients of several popular algorithms popular in Computational Optimal Transport, including the Sinkhorn algorithms, Wasserstein…

最优化与控制 · 数学 2025-12-04 Fangzhou Xie

This article introduces a new class of fast algorithms to approximate variational problems involving unbalanced optimal transport. While classical optimal transport considers only normalized probability distributions, it is important for…

最优化与控制 · 数学 2017-05-23 Lenaic Chizat , Gabriel Peyré , Bernhard Schmitzer , François-Xavier Vialard