English
Related papers

Related papers: Sinkhorn Flow: A Continuous-Time Framework for Und…

200 papers

We introduce a novel discretization scheme for Wasserstein gradient flows that involves successively computing Schr\"{o}dinger bridges with the same marginals. This is different from both the forward/geodesic approximation and the…

Probability · Mathematics 2024-06-18 Medha Agarwal , Zaid Harchaoui , Garrett Mulcahy , Soumik Pal

The matrix scaling problem, particularly the Sinkhorn-Knopp algorithm, has been studied for over 60 years. In practice, the algorithm often yields high-quality approximations within just a few iterations. Theoretically, however, the…

Data Structures and Algorithms · Computer Science 2025-08-12 Kun He

The stochastic mirror descent (SMD) algorithm is a general class of training algorithms, which includes the celebrated stochastic gradient descent (SGD), as a special case. It utilizes a mirror potential to influence the implicit bias of…

Machine Learning · Computer Science 2022-10-28 Taylan Kargin , Fariborz Salehi , Babak Hassibi

We present faster approximation algorithms for generalized network flow problems. A generalized flow is one in which the flow out of an edge differs from the flow into the edge by a constant factor. We limit ourselves to the lossy case,…

Data Structures and Algorithms · Computer Science 2008-04-07 Samuel I. Daitch , Daniel A. Spielman

The Wasserstein distance received a lot of attention recently in the community of machine learning, especially for its principled way of comparing distributions. It has found numerous applications in several hard problems, such as domain…

Machine Learning · Statistics 2017-10-23 Nicolas Courty , Rémi Flamary , Mélanie Ducoffe

We examine the continuous-time counterpart of mirror descent, namely mirror flow, on classification problems which are linearly separable. Such problems are minimised `at infinity' and have many possible solutions; we study which solution…

Machine Learning · Statistics 2024-11-14 Scott Pesme , Radu-Alexandru Dragomir , Nicolas Flammarion

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…

Machine Learning · Statistics 2018-03-06 Brahim Khalil Abid , Robert M. Gower

We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures. After identifying neglectable components of the dual solution of the regularized Sinkhorn problem, we propose to…

Machine Learning · Statistics 2020-01-22 Mokhtar Z. Alaya , Maxime Bérar , Gilles Gasso , Alain Rakotomamonjy

In this paper, we study the stochastic Hamiltonian flow in Wasserstein manifold, the probability density space equipped with $L^2$-Wasserstein metric tensor, via the Wong--Zakai approximation. We begin our investigation by showing that the…

Probability · Mathematics 2021-12-01 Jianbo Cui , Shu Liu , Haomin Zhou

Online learning algorithms are fast, memory-efficient, easy to implement, and applicable to many prediction problems, including classification, regression, and ranking. Several online algorithms were proposed in the past few decades, some…

Machine Learning · Computer Science 2015-07-03 Francesco Orabona , Koby Crammer , Nicolò Cesa-Bianchi

We study the Wasserstein gradient flow of the Sinkhorn divergence when both the source and the target are Gaussian distributions. We prove the existence of a flow that stays in the class of Gaussian distributions, and is unique in the…

Analysis of PDEs · Mathematics 2026-02-20 Mathis Hardion , Théo Lacombe

Hamilton's equations of motion form a fundamental framework in various branches of physics, including astronomy, quantum mechanics, particle physics, and climate science. Classical numerical solvers are typically employed to compute the…

Machine Learning · Computer Science 2024-10-25 Priscilla Canizares , Davide Murari , Carola-Bibiane Schönlieb , Ferdia Sherry , Zakhar Shumaylov

We provide theoretical analyses for two algorithms that solve the regularized optimal transport (OT) problem between two discrete probability measures with at most $n$ atoms. We show that a greedy variant of the classical Sinkhorn…

Data Structures and Algorithms · Computer Science 2021-07-27 Tianyi Lin , Nhat Ho , Michael I. Jordan

We study optimization problems whereby the optimization variable is a probability measure. Since the probability space is not a vector space, many classical and powerful methods for optimization (e.g., gradients) are of little help. Thus,…

Optimization and Control · Mathematics 2024-06-18 Nicolas Lanzetti , Antonio Terpin , Florian Dörfler

Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that optimizers typically operate in a complex, oscillatory regime…

Machine Learning · Computer Science 2025-09-26 Jeremy M. Cohen , Alex Damian , Ameet Talwalkar , J. Zico Kolter , Jason D. Lee

For a broad class of models widely used in practice for choice and ranking data based on Luce's choice axiom, including the Bradley--Terry--Luce and Plackett--Luce models, we show that the associated maximum likelihood estimation problems…

Optimization and Control · Mathematics 2025-04-08 Zhaonan Qu , Alfred Galichon , Wenzhi Gao , Johan Ugander

Data unfolding -- the removal of noise or artifacts from measurements -- is a fundamental task across the experimental sciences. Of particular interest are applications in physics, where the dominant approach is Richardson-Lucy (RL)…

Optimization and Control · Mathematics 2026-04-24 Katy Craig , Benjamin Faktor , Benjamin Nachman

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…

Optimization and Control · Mathematics 2015-03-10 Gabriel Peyré

We propose Acc-Sinkhorn, a simple accelerated variant of Sinkhorn for entropy-regularized optimal transport (EOT). The method is derived from a bilevel optimization view: Sinkhorn row scaling solves the inner variable $u$ exactly and…

Optimization and Control · Mathematics 2026-05-29 Zeyi Xu , Long Chen

While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative…

Machine Learning · Computer Science 2025-10-20 Mingyang Sun , Pengxiang Ding , Weinan Zhang , Donglin Wang
‹ Prev 1 4 5 6 7 8 10 Next ›