English
Related papers

Related papers: Joint Metric Space Embedding by Unbalanced OT with…

200 papers

Multi-marginal optimal transport enables one to compare multiple probability measures, which increasingly finds application in multi-task learning problems. One practical limitation of multi-marginal transport is computational scalability…

The Gromov-Wasserstein (GW) problem provides a powerful framework for aligning heterogeneous datasets by matching their internal structures in a way that minimizes distortion. However, GW alignment is sensitive to data contamination by…

Statistics Theory · Mathematics 2025-06-27 Xiaoyun Gong , Sloan Nietert , Ziv Goldfeld

Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation. However, addressing this…

Machine Learning · Computer Science 2019-11-05 Jiezhang Cao , Langyuan Mo , Yifan Zhang , Kui Jia , Chunhua Shen , Mingkui Tan

We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances between input and embedding samples are computed through a…

Machine Learning · Computer Science 2023-10-06 Hugues Van Assel , Cédric Vincent-Cuaz , Titouan Vayer , Rémi Flamary , Nicolas Courty

The Gromov-Wasserstein (GW) distance is frequently used in machine learning to compare distributions across distinct metric spaces. Despite its utility, it remains computationally intensive, especially for large-scale problems. Recently, a…

Machine Learning · Statistics 2024-10-01 Antoine Salmona , Julie Delon , Agnès Desolneux

Multi-view data analysis seeks to integrate multiple representations of the same samples in order to recover a coherent low-dimensional structure. Classical approaches often rely on feature concatenation or explicit alignment assumptions,…

The Gromov-Wasserstein (GW) framework adapts ideas from optimal transport to allow for the comparison of probability distributions defined on different metric spaces. Scalable computation of GW distances and associated matchings on graphs…

Machine Learning · Computer Science 2021-05-05 Samir Chowdhury , David Miller , Tom Needham

The Gromov-Wasserstein (GW) distance is an effective measure of alignment between distributions supported on distinct ambient spaces. Calculating essentially the mutual departure from isometry, it has found vast usage in domain translation…

Machine Learning · Statistics 2024-12-23 Anish Chakrabarty , Arkaprabha Basu , Swagatam Das

This paper presents a framework for computing the Gromov-Wasserstein problem between two sets of points in low dimensional spaces, where the discrepancy is the squared Euclidean norm. The Gromov-Wasserstein problem is a generalization of…

Optimization and Control · Mathematics 2023-07-19 Martin Ryner , Jan Kronqvist , Johan Karlsson

Optimal Transport (OT) has recently emerged as a central tool in data sciences to compare in a geometrically faithful way point clouds and more generally probability distributions. The wide adoption of OT into existing data analysis and…

Machine Learning · Statistics 2023-01-18 Thibault Séjourné , Gabriel Peyré , François-Xavier Vialard

Gromov-Wasserstein distance has found many applications in machine learning due to its ability to compare measures across metric spaces and its invariance to isometric transformations. However, in certain applications, this invariance…

Machine Learning · Computer Science 2023-07-20 Pinar Demetci , Quang Huy Tran , Ievgen Redko , Ritambhara Singh

Gromov--Wasserstein optimal transport (GWOT) aligns metric measure spaces by matching their within-domain relational structures, but large-scale GWOT remains challenging because its objective is nonconvex and projection onto the transport…

Machine Learning · Computer Science 2026-05-07 Ling Liang , Lei Yang

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any…

Machine Learning · Computer Science 2017-11-21 Yukun Chen , Jianbo Ye , Jia Li

Optimal Transport is a theory that allows to define geometrical notions of distance between probability distributions and to find correspondences, relationships, between sets of points. Many machine learning applications are derived from…

Machine Learning · Statistics 2020-11-10 Titouan Vayer

Aligning data from different domains is a fundamental problem in machine learning with broad applications across very different areas, most notably aligning experimental readouts in single-cell multiomics. Mathematically, this problem can…

Machine Learning · Computer Science 2024-06-21 Sanketh Vedula , Valentino Maiorca , Lorenzo Basile , Francesco Locatello , Alex Bronstein

Optimal transport (OT) and the related Wasserstein metric (W) are powerful and ubiquitous tools for comparing distributions. However, computing pairwise Wasserstein distances rapidly becomes intractable as cohort size grows. An attractive…

Machine Learning · Computer Science 2024-06-05 Doron Haviv , Russell Zhang Kunes , Thomas Dougherty , Cassandra Burdziak , Tal Nawy , Anna Gilbert , Dana Pe'er

The relevance of optimal transport methods to machine learning has long been hindered by two salient limitations. First, the $O(n^3)$ computational cost of standard sample-based solvers (when used on batches of $n$ samples) is prohibitive.…

Machine Learning · Computer Science 2023-06-01 Meyer Scetbon , Michal Klein , Giovanni Palla , Marco Cuturi

Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using…

Machine Learning · Computer Science 2019-09-04 François-Pierre Paty , Marco Cuturi

In this paper, we present an ensemble data assimilation paradigm over a Riemannian manifold equipped with the Wasserstein metric. Unlike the Eulerian penalization of error in the Euclidean space, the Wasserstein metric can capture…

Methodology · Statistics 2021-10-11 Sagar K. Tamang , Ardeshir Ebtehaj , Peter J. Van Leeuwen , Dongmian Zou , Gilad Lerman

Dimension reduction techniques typically seek an embedding of a high-dimensional point cloud into a low-dimensional Euclidean space which optimally preserves the geometry of the input data. Based on expert knowledge, one may instead wish to…

Optimization and Control · Mathematics 2025-02-28 Ranthony A. Clark , Tom Needham , Thomas Weighill