English
Related papers

Related papers: Sliced Inner Product Gromov-Wasserstein Distances

200 papers

The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues. Motivated by the important question of characterizing the geometrical properties of the generated distributions, we provide a…

Machine Learning · Statistics 2023-10-06 Arthur Stéphanovitch , Ugo Tanielian , Benoît Cadre , Nicolas Klutchnikoff , Gérard Biau

Supervised graph prediction addresses regression problems where the outputs are structured graphs. Although several approaches exist for graph-valued prediction, principled uncertainty quantification remains limited. We propose a conformal…

Machine Learning · Statistics 2026-03-30 Gabriel Melo , Thibaut de Saivre , Anna Calissano , Florence d'Alché-Buc

Sliced Inverse Regression (SIR) is an effective method for dimension reduction in high-dimensional regression problems. The original method, however, requires the inversion of the predictors covariance matrix. In case of collinearity…

Statistics Theory · Mathematics 2011-04-01 C. Bernard-Michel , L. Gardes , S. Girard

We study the problem of quantifying how far an empirical distribution deviates from Gaussianity under the framework of optimal transport. By exploiting the cone geometry of the relative translation invariant quadratic Wasserstein space, we…

Machine Learning · Computer Science 2026-02-02 Binshuai Wang , Peng Wei

The literature postulates that the dynamic time warping (dtw) distance can cope with temporal variations but stores and processes time series in a form as if the dtw-distance cannot cope with such variations. To address this inconsistency,…

Machine Learning · Computer Science 2019-03-11 Brijnesh Jain

Minimizing functionals in the space of probability distributions can be done with Wasserstein gradient flows. To solve them numerically, a possible approach is to rely on the Jordan-Kinderlehrer-Otto (JKO) scheme which is analogous to the…

Machine Learning · Computer Science 2022-11-16 Clément Bonet , Nicolas Courty , François Septier , Lucas Drumetz

The squared Wasserstein distance is a natural quantity to compare probability distributions in a non-parametric setting. This quantity is usually estimated with the plug-in estimator, defined via a discrete optimal transport problem which…

Optimization and Control · Mathematics 2020-10-30 Lenaic Chizat , Pierre Roussillon , Flavien Léger , François-Xavier Vialard , Gabriel Peyré

We investigate a dynamic inverse problem using a regularization which implements the so-called Wasserstein-$1$ distance. It naturally extends well-known static problems such as lasso or total variation regularized problems to a (temporally)…

Optimization and Control · Mathematics 2025-12-05 Marcello Carioni , Julius Lohmann

This paper introduces a concrete relation between genus zero closed Gromov-Witten invariants of Calabi-Yau threefolds and genus zero open Gromov-Witten invariants of a Lagrangian $A$-brane in the same threefold. Symplectic cutting is a…

High Energy Physics - Theory · Physics 2025-01-13 Luca Cassia , Pietro Longhi , Maxim Zabzine

Pairwise comparison of graphs is key to many applications in Machine learning ranging from clustering, kernel-based classification/regression and more recently supervised graph prediction. Distances between graphs usually rely on…

Machine Learning · Statistics 2023-09-29 Junjie Yang , Matthieu Labeau , Florence d'Alché-Buc

The Wasserstein distance is a powerful metric based on the theory of optimal transport. It gives a natural measure of the distance between two distributions with a wide range of applications. In contrast to a number of the common…

Machine Learning · Computer Science 2021-02-16 Jung Hun Oh , Maryam Pouryahya , Aditi Iyer , Aditya P. Apte , Allen Tannenbaum , Joseph O. Deasy

This work characterizes, analytically and numerically, two major effects of the quadratic Wasserstein ($W_2$) distance as the measure of data discrepancy in computational solutions of inverse problems. First, we show, in the…

Numerical Analysis · Mathematics 2020-06-24 Bjorn Engquist , Kui Ren , Yunan Yang

Compared with word embedding based on point representation, distribution-based word embedding shows more flexibility in expressing uncertainty and therefore embeds richer semantic information when representing words. The Wasserstein…

Computation and Language · Computer Science 2018-09-05 Chi Sun , Hang Yan , Xipeng Qiu , Xuanjing Huang

Hydromagnetic turbulence produced during phase transitions in the early universe can be a powerful source of stochastic gravitational waves (GWs). GWs can be modelled by the linearised spatial part of the Einstein equations sourced by the…

Fluid Dynamics · Physics 2021-07-15 A. Roper Pol , A. Brandenburg , T. Kahniashvili , A. Kosowsky , S. Mandal

We propose a new nonlinear factorization model for graphs that are with topological structures, and optionally, node attributes. This model is based on a pseudometric called Gromov-Wasserstein (GW) discrepancy, which compares graphs in a…

Machine Learning · Computer Science 2019-11-21 Hongteng Xu

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

In this work, we propose a novel approach for subgraph matching, the problem of finding a given query graph in a large source graph, based on the fused Gromov-Wasserstein distance. We formulate the subgraph matching problem as a partial…

Information Theory · Computer Science 2024-07-01 Wen-Xin Pan , Isabel Haasler , Pascal Frossard

Sliced inverse regression is one of the most popular sufficient dimension reduction methods. Originally, it was designed for independent and identically distributed data and recently extend to the case of serially and spatially dependent…

Methodology · Statistics 2021-07-07 Christoph Muehlmann , Hannu Oja , Klaus Nordhausen

In this paper, we consider the problem of computing the integral of a function on the unit sphere, in any dimension, using Monte Carlo methods. Although the methods we present are general, our guiding thread is the sliced Wasserstein…

Machine Learning · Statistics 2026-03-11 Vladimir Petrovic , Rémi Bardenet , Agnès Desolneux

Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the…

Machine Learning · Statistics 2019-08-23 Leon Bottou , Martin Arjovsky , David Lopez-Paz , Maxime Oquab
‹ Prev 1 8 9 10 Next ›