English
Related papers

Related papers: Coreset selection for the Sinkhorn divergence and …

200 papers

As deep learning models continue to scale, the growing computational demands have amplified the need for effective coreset selection techniques. Coreset selection aims to accelerate training by identifying small, representative subsets of…

Machine Learning · Computer Science 2025-11-24 Wei-Kai Chang , Rajiv Khanna

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…

Optimization and Control · Mathematics 2023-01-18 Thibault Séjourné , Jean Feydy , François-Xavier Vialard , Alain Trouvé , Gabriel Peyré

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 real world, our datasets often contain outliers. Moreover, the outliers can seriously affect the final machine learning result. Most existing algorithms for handling outliers take high time complexities (e.g. quadratic or cubic…

Computational Geometry · Computer Science 2020-02-28 Hu Ding , Zixiu Wang

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…

Optimization and Control · Mathematics 2024-03-11 Xun Tang , Holakou Rahmanian , Michael Shavlovsky , Kiran Koshy Thekumparampil , Tesi Xiao , Lexing Ying

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

We introduce kernel thinning, a new procedure for compressing a distribution $\mathbb{P}$ more effectively than i.i.d. sampling or standard thinning. Given a suitable reproducing kernel $\mathbf{k}_{\star}$ and $O(n^2)$ time, kernel…

Machine Learning · Statistics 2024-05-14 Raaz Dwivedi , Lester Mackey

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…

Data Structures and Algorithms · Computer Science 2025-01-14 Kazuki Watanabe , Noboru Isobe

Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically…

Machine Learning · Computer Science 2024-03-01 Xiaobo Xia , Jiale Liu , Shaokun Zhang , Qingyun Wu , Hongxin Wei , Tongliang Liu

We introduce the Sinkhorn treatment effect, an entropic optimal transport measure of divergence between counterfactual distributions. Unlike classical quantities such as the average treatment effect, this measure captures differences across…

Machine Learning · Statistics 2026-05-12 Medha Agarwal , Alex Luedtke

The goal of coreset selection in supervised learning is to produce a weighted subset of data, so that training only on the subset achieves similar performance as training on the entire dataset. Existing methods achieved promising results in…

Machine Learning · Computer Science 2023-01-25 Xiao Zhou , Renjie Pi , Weizhong Zhang , Yong Lin , Tong Zhang

Bayesian coresets have emerged as a promising approach for implementing scalable Bayesian inference. The Bayesian coreset problem involves selecting a (weighted) subset of the data samples, such that the posterior inference using the…

Machine Learning · Statistics 2021-03-01 Jacky Y. Zhang , Rajiv Khanna , Anastasios Kyrillidis , Oluwasanmi Koyejo

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

As machine learning tasks continue to evolve, the trend has been to gather larger datasets and train increasingly larger models. While this has led to advancements in accuracy, it has also escalated computational costs to unsustainable…

Machine Learning · Computer Science 2024-06-03 Mohammad Jafari , Yimeng Zhang , Yihua Zhang , Sijia Liu

This contribution presents substantial computational advancements to compare measures even with varying masses. Specifically, we utilize the nonequispaced fast Fourier transform to accelerate the radial kernel convolution in unbalanced…

Optimization and Control · Mathematics 2024-05-15 Rajmadan Lakshmanan , Alois Pichler

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

We give relative error coresets for training linear classifiers with a broad class of loss functions, including the logistic loss and hinge loss. Our construction achieves $(1\pm \epsilon)$ relative error with $\tilde O(d \cdot…

Machine Learning · Computer Science 2021-06-21 Tung Mai , Anup B. Rao , Cameron Musco

Many problems in geometric optics or convex geometry can be recast as optimal transport problems: this includes the far-field reflector problem, Alexandrov's curvature prescription problem, etc. A popular way to solve these problems…

Numerical Analysis · Mathematics 2017-03-08 Jun Kitagawa , Quentin Mérigot , Boris Thibert

Training machine learning models on massive datasets incurs substantial computational costs. To alleviate such costs, there has been a sustained effort to develop data-efficient training methods that can carefully select subsets of the…

Machine Learning · Computer Science 2022-08-01 Omead Pooladzandi , David Davini , Baharan Mirzasoleiman

Data distillation and coresets have emerged as popular approaches to generate a smaller representative set of samples for downstream learning tasks to handle large-scale datasets. At the same time, machine learning is being increasingly…

‹ Prev 1 2 3 10 Next ›