English
Related papers

Related papers: Gromov-Wasserstein Transfer Operators

200 papers

We use the Ward identities corresponding to general linear transformations, and derive relations between transport coefficients of $(2+1)$-dimensional systems. Our analysis includes relativistic and Galilean invariant systems, as well as…

High Energy Physics - Theory · Physics 2015-03-30 Carlos Hoyos , Bom Soo Kim , Yaron Oz

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

Optimal transport theory has recently found many applications in machine learning thanks to its capacity for comparing various machine learning objects considered as distributions. The Kantorovitch formulation, leading to the Wasserstein…

Machine Learning · Statistics 2018-11-08 Titouan Vayer , Laetita Chapel , Rémi Flamary , Romain Tavenard , Nicolas Courty

This paper introduces a novel and generic framework to solve the flagship task of supervised labeled graph prediction by leveraging Optimal Transport tools. We formulate the problem as regression with the Fused Gromov-Wasserstein (FGW) loss…

Machine Learning · Statistics 2022-06-27 Luc Brogat-Motte , Rémi Flamary , Céline Brouard , Juho Rousu , Florence d'Alché-Buc

Many existing transductive bounds rely on classical complexity measures that are computationally intractable and often misaligned with empirical behavior. In this work, we establish new representation-based generalization bounds in a…

Machine Learning · Computer Science 2026-03-11 MoonJeong Park , Seungbeom Lee , Kyungmin Kim , Jaeseung Heo , Seunghyuk Cho , Shouheng Li , Sangdon Park , Dongwoo Kim

This paper gives a spectral approach to time asymptotics of collisionless transport semi-groups with general diffuse boundary operators. The strong stability of the invariant density is derived from the classical Ingham theorem. A recent…

Analysis of PDEs · Mathematics 2020-05-27 Bertrand Lods , Mustapha Mokhtar-Kharroubi

Optimal transport provides an inherently geometric and highly structured framework for studying spaces of probability measures, supplying a rich theoretical toolkit for contemporary statistics, machine learning, and generative modelling. In…

Statistics Theory · Mathematics 2026-05-21 Riccardo Passeggeri , Rohan M. Shenoy , Pengcheng Ye

This paper develops a tractable analytical channel model for first-hitting-time molecular communication (MC) systems under time-varying drift. While existing studies of nonstationary transport rely primarily on numerical solutions of…

Information Theory · Computer Science 2026-03-30 Yen-Chi Lee

The topic of this study lies in the intersection of two fields. One is related with analyzing transport phenomena in complicated flows.For this purpose, we use so-called coherent sets: non-dispersing, possibly moving regions in the flow's…

Numerical Analysis · Mathematics 2021-07-28 Péter Koltai , Johannes von Lindheim , Sebastian Neumayer , Gabriele Steidl

As a valid metric of metric-measure spaces, Gromov-Wasserstein (GW) distance has shown the potential for matching problems of structured data like point clouds and graphs. However, its application in practice is limited due to the high…

Machine Learning · Computer Science 2023-01-10 Mengyu Li , Jun Yu , Hongteng Xu , Cheng Meng

We propose a new driving scheme, when different parts of a system are driven with different, generally incommensurate, frequencies. Such driving provides a flexible handle to control various properties of the system and to obtain new types…

Optics · Physics 2018-03-01 Huanan Li , Tsampikos Kottos , Boris Shapiro

We study transport of local magnetization in a Heisenberg spin-1/2 chain at zero temperature. The system is initially prepared in a highly excited pure state far from equilibrium and its evolution is analyzed via exact diagonalization.…

Statistical Mechanics · Physics 2015-05-13 L. F. Santos

The Gaussian process (GP) is a nonparametric prior distribution over functions indexed by time, space, or other high-dimensional index set. The GP is a flexible model yet its limitation is given by its very nature: it can only model…

Machine Learning · Statistics 2019-07-15 Gonzalo Rios , Felipe Tobar

In molecular dynamics, transport coefficients measure the sensitivity of the invariant probability measure of the stochastic dynamics at hand with respect to some perturbation. They are typically computed using either the linear response of…

Numerical Analysis · Mathematics 2025-02-19 Pierre Monmarché , Renato Spacek , Gabriel Stoltz

We present a graph random walk (GRW) method for the study of charge transport properties of complex molecular materials in the time-of-flight regime. The molecules forming the material are represented by the vertices of a directed weighted…

Statistical Mechanics · Physics 2025-04-01 Zhongquan Chen , Pim van der Hoorn , Björn Baumeier

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

We present a dynamical and spectral study of Ostrowski's map based on the use of transfer operators. The Ostroswki dynamical system is obtained as a skew-product of the Gauss map (it has the Gauss map as a base and interval fibers) and…

Dynamical Systems · Mathematics 2023-07-20 Valérie Berthé , Jungwon Lee

We develop statistical models for samples of distribution-valued stochastic processes featuring time-indexed univariate distributions, with emphasis on functional principal component analysis. The proposed model presents an intrinsic rather…

Methodology · Statistics 2024-06-21 Hang Zhou , Hans-Georg Müller

The standard noise model in gravitational wave (GW) data analysis assumes detector noise is stationary and Gaussian distributed, with a known power spectral density (PSD) that is usually estimated using clean off-source data. Real GW data…

General Relativity and Quantum Cosmology · Physics 2015-09-16 Matthew C. Edwards , Renate Meyer , Nelson Christensen

Score-based diffusion models currently constitute the state of the art in continuous generative modeling. These methods are typically formulated via overdamped or underdamped Ornstein--Uhlenbeck-type stochastic differential equations, in…

Machine Learning · Computer Science 2025-12-22 Herlock Rahimi