English
Related papers

Related papers: Better and Simpler Error Analysis of the Sinkhorn-…

200 papers

We study Sinkhorn EM (sEM), a variant of the expectation maximization (EM) algorithm for mixtures based on entropic optimal transport. sEM differs from the classic EM algorithm in the way responsibilities are computed during the expectation…

Machine Learning · Statistics 2020-07-01 Gonzalo Mena , Amin Nejatbakhsh , Erdem Varol , Jonathan Niles-Weed

We prove that the Sinkhorn algorithm converges at a rate of $O(k^{-1} \log k)$ in $\ell_1$-norm marginal error, in the asymptotically scalable case. This almost closes the gap between the lower bound $\Omega(k^{-1})$ (Qu et al., 2025) and…

Optimization and Control · Mathematics 2026-05-15 Guillaume Wang

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

Random sampling has become a critical tool in solving massive matrix problems. For linear regression, a small, manageable set of data rows can be randomly selected to approximate a tall, skinny data matrix, improving processing time…

Data Structures and Algorithms · Computer Science 2014-08-22 Michael B. Cohen , Yin Tat Lee , Cameron Musco , Christopher Musco , Richard Peng , Aaron Sidford

The Kruithof iterative scaling process, which adjusts matrices to meet target row and column sums, is a longstanding problem that lacks a general closed form for its limit. While Nathanson derived the closed form for the Sinkhorn limit of…

General Mathematics · Mathematics 2025-06-18 Max Chicky Fang

The Wasserstein metric is broadly used in optimal transport for comparing two probabilistic distributions, with successful applications in various fields such as machine learning, signal processing, seismic inversion, etc. Nevertheless, the…

Optimization and Control · Mathematics 2022-02-22 Qichen Liao , Jing Chen , Zihao Wang , Bo Bai , Shi Jin , Hao Wu

Kernel methods are used frequently in various applications of machine learning. For large-scale high dimensional applications, the success of kernel methods hinges on the ability to operate certain large dense kernel matrix K. An enormous…

Numerical Analysis · Mathematics 2021-12-30 Difeng Cai , James Nagy , Yuanzhe Xi

The Lasso is one of the most important approaches for parameter estimation and variable selection in high dimensional linear regression. At the heart of its success is the attractive rate of convergence result even when $p$, the dimension…

Statistics Theory · Mathematics 2019-08-09 Junlong Zhao , Chenlei Leng

We develop several efficient algorithms for the classical \emph{Matrix Scaling} problem, which is used in many diverse areas, from preconditioning linear systems to approximation of the permanent. On an input $n\times n$ matrix $A$, this…

Data Structures and Algorithms · Computer Science 2017-04-10 Zeyuan Allen-Zhu , Yuanzhi Li , Rafael Oliveira , Avi Wigderson

This paper addresses matrix approximation problems for matrices that are large, sparse and/or that are representations of large graphs. To tackle these problems, we consider algorithms that are based primarily on coarsening techniques,…

Numerical Analysis · Computer Science 2018-10-03 Shashanka Ubaru , Yousef Saad

This article describes a set of methods for quickly computing the solution to the regularized optimal transport problem. It generalizes and improves upon the widely-used iterative Bregman projections algorithm (or Sinkhorn--Knopp…

Numerical Analysis · Mathematics 2021-04-02 Alexis Thibault , Lénaïc Chizat , Charles Dossal , Nicolas Papadakis

We extend Random Access, a fundamental operation that enables efficient search and exploration algorithms, to the modern interactive data systems based on Ranked Retrieval and Similarity Search, where orderings are dynamically defined over…

Data Structures and Algorithms · Computer Science 2026-05-26 Mohsen Dehghankar , Abolfazl Asudeh , Raghav Mittal , Suraj Shetiya , Gautam Das

We study three fundamental problems of Linear Algebra, lying in the heart of various Machine Learning applications, namely: 1)"Low-rank Column-based Matrix Approximation". We are given a matrix A and a target rank k. The goal is to select a…

Data Structures and Algorithms · Computer Science 2011-05-05 Christos Boutsidis

Kernel $k$-means clustering can correctly identify and extract a far more varied collection of cluster structures than the linear $k$-means clustering algorithm. However, kernel $k$-means clustering is computationally expensive when the…

Machine Learning · Computer Science 2019-02-12 Shusen Wang , Alex Gittens , Michael W. Mahoney

Low-rank matrix regression is a fundamental problem in data science with various applications in systems and control. Nuclear norm regularization has been widely applied to solve this problem due to its convexity. However, it suffers from…

Systems and Control · Electrical Eng. & Systems 2025-06-04 Mingzhou Yin , Matthias A. Müller

The optimal mass transport problem gives a geometric framework for optimal allocation, and has recently gained significant interest in application areas such as signal processing, image processing, and computer vision. Even though it can be…

Optimization and Control · Mathematics 2018-02-07 Johan Karlsson , Axel Ringh

The Column Subset Selection Problem (CSSP) and the Nystr\"om method are among the leading tools for constructing small low-rank approximations of large datasets in machine learning and scientific computing. A fundamental question in this…

Machine Learning · Computer Science 2020-12-22 Michał Dereziński , Rajiv Khanna , Michael W. Mahoney

The purpose of this work is to develop a framework to calibrate signed datasets so as to be consistent with specified marginals by suitably extending the Schr\"odinger-Fortet-Sinkhorn paradigm. Specifically, we seek to revise…

Machine Learning · Statistics 2023-08-24 Anqi Dong , Tryphon T. Georgiou , Allen Tannenbaum

Assume that f is a strict convex function with a unique minimum in R^n. We divide the vector of n-variables to d groups of vector subvariables with d at least two. We assume that we can find the partial minimum of f with respect to each…

Optimization and Control · Mathematics 2019-06-06 Shmuel Friedland

We consider the problem of reconstructing rank-one matrices from random linear measurements, a task that appears in a variety of problems in signal processing, statistics, and machine learning. In this paper, we focus on the Alternating…

Machine Learning · Computer Science 2022-04-26 Kiryung Lee , Dominik Stöger