中文
相关论文

相关论文: On the contraction properties of Sinkhorn semigrou…

200 篇论文

Entropic optimal transport problems play an increasingly important role in machine learning and generative modelling. In contrast with optimal transport maps which often have limited applicability in high dimensions, Schrodinger bridges can…

概率论 · 数学 2026-01-21 Pierre Del Moral , Ajay Jasra

We develop a quantitative contraction framework for Schrodinger and Sinkhorn bridges based on transportation-cost inequalities and Riccati matrix difference equations. Our approach combines logarithmic Sobolev and Talagrand-type…

最优化与控制 · 数学 2026-01-21 Pierre Del Moral

This paper develops a novel operator theoretic framework to study the contraction properties of Markov semigroups with respect to a general class of Kantorovich semi-distances, which notably includes Wasserstein distances. The rather simple…

概率论 · 数学 2026-03-04 Pierre Del Moral , Mathieu Gerber

In this paper we determine quantitative stability bounds for the Hessian of entropic potentials, \ie, the dual solution to the entropic optimal transport problem. To the authors' knowledge this is the first work addressing this second-order…

概率论 · 数学 2025-11-14 Giacomo Greco , Luca Tamanini

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

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

Entropic optimal transport (OT) and the Sinkhorn algorithm have made it practical for machine learning practitioners to perform the fundamental task of calculating transport distance between statistical distributions. In this work, we focus…

We show non-asymptotic exponential convergence of Sinkhorn iterates to the Schr\"odinger potentials, solutions of the quadratic Entropic Optimal Transport problem on $\mathbb{R}^ d$. Our results hold under mild assumptions on the marginal…

概率论 · 数学 2026-05-01 Giovanni Conforti , Alain Durmus , Giacomo Greco

We establish the uniform in time stability, w.r.t. the marginals, of the Iterative Proportional Fitting Procedure, also known as Sinkhorn algorithm, used to solve entropy-regularised Optimal Transport problems. Our result is quantitative…

机器学习 · 统计学 2021-10-25 George Deligiannidis , Valentin De Bortoli , Arnaud Doucet

Entropy-regularized optimal transport, which has strong links to the Schr\"odinger bridge problem in statistical mechanics, enjoys a variety of applications from trajectory inference to generative modeling. A major driver of renewed…

机器学习 · 统计学 2026-01-27 Anand Srinivasan , Jean-Jacques Slotine

We study the convergence rate of Sinkhorn's algorithm for solving entropy-regularized optimal transport problems when at least one of the probability measures, $\mu$, admits a density over $\mathbb{R}^d$. For a semi-concave cost function…

最优化与控制 · 数学 2025-07-21 Lénaïc Chizat , Alex Delalande , Tomas Vaškevičius

We study the stability of entropically regularized optimal transport with respect to the marginals. Given marginals converging weakly, we establish a strong convergence for the Schr\"odinger potentials describing the density of the optimal…

概率论 · 数学 2022-01-26 Marcel Nutz , Johannes Wiesel

The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence, has recently gained popularity in machine learning and statistics, as it makes feasible the use of smoothed optimal transportation distances for data…

统计理论 · 数学 2019-11-05 Jérémie Bigot , Elsa Cazelles , Nicolas Papadakis

Computing the optimal transport distance between statistical distributions is a fundamental task in machine learning. One remarkable recent advancement is entropic regularization and the Sinkhorn algorithm, which utilizes only matrix…

The stability and contraction properties of positive integral semigroups on Polish spaces are investigated. Our novel analysis is based on the extension of V-norm contraction methods, associated to functionally weighted Banach spaces for…

概率论 · 数学 2023-03-07 Pierre del Moral , Emma Horton , Ajay Jasra

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

We derive nearly tight and non-asymptotic convergence bounds for solutions of entropic semi-discrete optimal transport. These bounds quantify the stability of the dual solutions of the regularized problem (sometimes called Sinkhorn…

人工智能 · 计算机科学 2022-05-05 Alex Delalande

Contraction theory for dynamical systems on Euclidean spaces is well-established. For contractive (resp. semi-contractive) systems, the distance (resp. semi-distance) between any two trajectories decreases exponentially fast. For partially…

最优化与控制 · 数学 2021-06-07 Pedro Cisneros-Velarde , Saber Jafarpour , Francesco Bullo

The article presents new entropic continuity bounds for conditional expectations and conditional covariance matrices. These bounds are expressed in terms of the relative entropy between different coupling distributions. Our approach…

概率论 · 数学 2025-04-29 Pierre Del Moral

Sinkhorn algorithm is the de-facto standard approximation algorithm for optimal transport, which has been applied to a variety of applications, including image processing and natural language processing. In theory, the proof of its…

数据结构与算法 · 计算机科学 2025-01-14 Kazuki Watanabe , Noboru Isobe
‹ 上一页 1 2 3 10 下一页 ›