English
Related papers

Related papers: Sample Complexity of Sinkhorn divergences

200 papers

Estimating Wasserstein distances between two high-dimensional densities suffers from the curse of dimensionality: one needs an exponential (wrt dimension) number of samples to ensure that the distance between two empirical measures is…

Machine Learning · Statistics 2020-07-13 François-Pierre Paty , Alexandre d'Aspremont , Marco Cuturi

We provide a computational complexity analysis for the Sinkhorn algorithm that solves the entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures of possibly different masses with at most $n$ components. We show…

Computational Complexity · Computer Science 2020-11-20 Khiem Pham , Khang Le , Nhat Ho , Tung Pham , Hung Bui

Regularized optimal transport (OT) is now increasingly used as a loss or as a matching layer in neural networks. Entropy-regularized OT can be computed using the Sinkhorn algorithm but it leads to fully-dense transportation plans, meaning…

Machine Learning · Statistics 2023-04-17 Tianlin Liu , Joan Puigcerver , Mathieu Blondel

We investigate the semi-discrete Optimal Transport (OT) problem, where a continuous source measure $\mu$ is transported to a discrete target measure $\nu$, with particular attention to the OT map approximation. In this setting, Stochastic…

It is well known that under general regularity conditions the distribution of the maximum likelihood estimator (MLE) is asymptotically normal. Very recently, bounds of the optimal order $O(1/\sqrt n)$ on the closeness of the distribution of…

Statistics Theory · Mathematics 2016-12-15 Iosif Pinelis

The ability to compare two degenerate probability distributions (i.e. two probability distributions supported on two distinct low-dimensional manifolds living in a much higher-dimensional space) is a crucial problem arising in the…

Machine Learning · Statistics 2017-10-23 Aude Genevay , Gabriel Peyré , Marco Cuturi

The optimal transport (OT) problem is a classical optimization problem having the form of linear programming. Machine learning applications put forward new computational challenges in its solution. In particular, the OT problem defines a…

Optimization and Control · Mathematics 2022-10-25 Nazarii Tupitsa , Pavel Dvurechensky , Darina Dvinskikh , Alexander Gasnikov

Solving large scale Optimal Transport (OT) in machine learning typically relies on sampling measures to obtain a tractable discrete problem. While the discrete solver's accuracy is controllable, the rate of convergence of the discretization…

Machine Learning · Statistics 2026-02-05 Ferdinand Genans , Olivier Wintenberger

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…

Statistics Theory · Mathematics 2024-12-10 Bernard Bercu , Jérémie Bigot

Computing optimal transport (OT) distances such as the earth mover's distance is a fundamental problem in machine learning, statistics, and computer vision. In this paper, we study the problem of approximating the general OT distance…

Data Structures and Algorithms · Computer Science 2023-01-18 Zhao Song , Tianyi Zhou

This paper presents consideration of the Semi-Relaxed Sinkhorn (SR-Sinkhorn) algorithm for the semi-relaxed optimal transport (SROT) problem, which relaxes one marginal constraint of the standard OT problem. For evaluation of how the…

Machine Learning · Computer Science 2022-05-30 Takumi Fukunaga , Hiroyuki Kasai

Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions. For instance, OT is a popular loss function that quantifies the discrepancy between an…

Machine Learning · Computer Science 2022-12-27 Shintaro Nakamura , Han Bao , Masashi Sugiyama

Computational optimal transport (OT) has recently emerged as a powerful framework with applications in various fields. In this paper we focus on a relaxation of the original OT problem, the entropic OT problem, which allows to implement…

Probability · Mathematics 2025-10-06 Giacomo Greco , Maxence Noble , Giovanni Conforti , Alain Durmus

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…

Statistics Theory · Mathematics 2019-11-05 Jérémie Bigot , Elsa Cazelles , Nicolas Papadakis

We study the tradeoff between sample complexity and round complexity in on-demand sampling, where the learning algorithm adaptively samples from $k$ distributions over a limited number of rounds. In the realizable setting of…

Machine Learning · Computer Science 2025-11-20 Nika Haghtalab , Omar Montasser , Mingda Qiao

Although Sinkhorn divergences are now routinely used in data sciences to compare probability distributions, the computational effort required to compute them remains expensive, growing in general quadratically in the size $n$ of the support…

Machine Learning · Statistics 2020-10-27 Meyer Scetbon , Marco Cuturi

Sinkhorn divergence is a measure of dissimilarity between two probability measures. It is obtained through adding an entropic regularization term to Kantorovich's optimal transport problem and can hence be viewed as an entropically…

Numerical Analysis · Mathematics 2020-05-01 Mohammad Motamed

Optimal Transport (OT) has established itself as a robust framework for quantifying differences between distributions, with applications that span fields such as machine learning, data science, and computer vision. This paper offers a…

Data Structures and Algorithms · Computer Science 2025-01-14 Sina Moradi

Optimal transport (OT) and Gromov-Wasserstein (GW) alignment are powerful frameworks for geometrically driven matching of probability distributions, yet their large-scale usage is hampered by high statistical and computational costs.…

Statistics Theory · Mathematics 2026-02-04 Tao Wang , Ziv Goldfeld

Popular machine learning estimators involve regularization parameters that can be challenging to tune, and standard strategies rely on grid search for this task. In this paper, we revisit the techniques of approximating the regularization…

Machine Learning · Statistics 2019-05-28 Eugene Ndiaye , Tam Le , Olivier Fercoq , Joseph Salmon , Ichiro Takeuchi