English
Related papers

Related papers: Smooth transport map via diffusion process

200 papers

The Green-Kubo theory of thermal transport has long be considered incompatible with modern simulation methods based on electronic-structure theory, because it is based on such concepts as energy density and current, which are ill-defined at…

Statistical Mechanics · Physics 2018-08-20 Stefano Baroni , Riccardo Bertossa , Loris Ercole , Federico Grasselli , Aris Marcolongo

Optimal transport (OT) has become a natural framework for guiding the probability flows. Yet, the majority of recent generative models assume trivial geometry (e.g., Euclidean) and rely on strong density-estimation assumptions, yielding…

Machine Learning · Computer Science 2025-09-23 Nazar Buzun , Daniil Shlenskii , Maxim Bobrin , Dmitry V. Dylov

We study heat conduction and momentum transport in the context of stochastic fluid dynamics. We consider a fluid described by model H in the classification of Hohenberg and Halperin. We study both non-critical and critical fluids, and we…

Nuclear Theory · Physics 2025-12-03 Chandrodoy Chattopadhyay , Josh Ott , Thomas Schaefer , Vladimir V. Skokov

We propose to tackle the problem of understanding the effect of regularization in Sinkhorn algotihms. In the case of Gaussian distributions we provide a closed form for the regularized optimal transport which enables to provide a better…

Statistics Theory · Mathematics 2020-06-16 Eustasio del Barrio , Jean-Michel Loubes

We show that the relativistic dynamics in a Gaussian random electromagnetic field can be approximated by the relativistic diffusion of Schay and Dudley. Lorentz invariant dynamics in the proper time leads to the diffusion in the proper…

Mathematical Physics · Physics 2015-05-27 Z. Haba

We study the quantitative stability of the mapping that to a measure associates its pushforward measure by a fixed (non-smooth) optimal transport map. We exhibit a tight H\"older-behavior for this operation under minimal assumptions. Our…

Optimization and Control · Mathematics 2024-01-08 Guillaume Carlier , Alex Delalande , Quentin Mérigot

We consider transport properties of the chaotic (strange) attractor along unfolded trajectories of the dissipative standard map. It is shown that the diffusion process is normal except of the cases when a control parameter is close to some…

Chaotic Dynamics · Physics 2009-11-13 G. M. Zaslavsky , M. Edelman

Let M and \bar M be n-dimensional manifolds equipped with suitable Borel probability measures \rho and \bar\rho. Ma, Trudinger & Wang gave sufficient conditions on a transportation cost c \in C^4(M \times \bar M) to guarantee smoothness of…

Differential Geometry · Mathematics 2007-12-20 Young-Heon Kim , Robert J. McCann

In this note, we propose a probabilistic approach to bound the (dimension-free) Lipschitz constant of the Langevin flow map on $\mathbb{R}^d$ introduced by Kim and Milman (2012). As example of application, we construct Lipschitz maps from a…

Probability · Mathematics 2025-02-04 Giovanni Conforti , Katharina Eichinger

Using quantum gas microscopy we study the late-time effective hydrodynamics of an isolated cold-atom Fermi-Hubbard system subject to an external linear potential (a "tilt"). The tilt is along one of the principal directions of the…

We derive a universal bound on generalized currents in Langevin systems in terms of the mean-square fluctuations of the current and the total entropy production. This bound generalizes a relation previously found by Barato et al. to…

Statistical Mechanics · Physics 2018-06-29 Andreas Dechant , Shin-ichi Sasa

We consider a process given as the solution of a one-dimensional stochastic differential equation with irregular, path dependent and time-inhomogeneous drift coefficient and additive noise. H\"older continuity of the Lebesgue density of…

Probability · Mathematics 2016-04-28 David Baños , Paul Krühner

We provide a clarification of the description of Langevin diffusions on Riemannian manifolds and of the measure underlying the invariant density. As a result we propose a new position-dependent Metropolis-adjusted Langevin algorithm (MALA)…

Methodology · Statistics 2014-08-15 Tatiana Xifara , Chris Sherlock , Samuel Livingstone , Simon Byrne , Mark Girolami

Heat fluctuations over a time \tau in a non-equilibrium stationary state and in a transient state are studied for a simple system with deterministic and stochastic components: a Brownian particle dragged through a fluid by a harmonic…

Statistical Mechanics · Physics 2007-05-23 R. van Zon , E. G. D. Cohen

Estimating optimal transport maps between two distributions from respective samples is an important element for many machine learning methods. To do so, rather than extending discrete transport maps, it has been shown that estimating the…

Statistics Theory · Mathematics 2025-02-04 Clément Lalanne , Franck Iutzeler , Jean-Michel Loubes , Julien Chhor

We study Neural Optimal Transport in infinite-dimensional Hilbert spaces. In non-regular settings, Semi-dual Neural OT often generates spurious solutions that fail to accurately capture target distributions. We analytically characterize…

Machine Learning · Computer Science 2026-02-17 Jae-Hwan Choi , Jiwoo Yoon , Dohyun Kwon , Jaewoong Choi

We provide a stochastic fractional diffusion equation description of energy transport through a finite one-dimensional chain of harmonic oscillators with stochastic momentum exchange and connected to Langevian type heat baths at the…

Statistical Mechanics · Physics 2019-05-22 Aritra Kundu , Cédric Bernardin , Keji Saito , Anupam Kundu , Abhishek Dhar

We work out the non-equilibrium steady state properties of a harmonic lattice which is connected to heat reservoirs at different temperatures. The heat reservoirs are themselves modeled as harmonic systems. Our approach is to write quantum…

Mesoscale and Nanoscale Physics · Physics 2009-11-11 Abhishek Dhar , Dibyendu Roy

We show that the nonperturbative quantum transport equations, the `Kadanoff-Baym equations', can be understood as the ensemble average over stochastic equations of Langevin type. For this we couple a free scalar boson quantum field to an…

High Energy Physics - Phenomenology · Physics 2017-08-23 C. Greiner , S. Leupold

We construct a transport map from Poisson point processes onto ultra-log-concave measures over the natural numbers, and show that this map is a contraction. Our approach overcomes the known obstacles to transferring functional inequalities…

Probability · Mathematics 2025-02-07 Pablo López-Rivera , Yair Shenfeld