From large deviations to Wasserstein gradient flows in multiple dimensions

被引:19
|
作者
Erbar, Matthias [1 ]
Maas, Jan [2 ]
Renger, D. R. Michiel [3 ]
机构
[1] Univ Bonn, Bonn, Germany
[2] Inst Sci & Technol Austria IST Austria, Klosterneuburg, Austria
[3] WIAS Berlin, Berlin, Germany
关键词
Large deviations; gradient flows; Wasserstein metric; Gamma-convergence; PRINCIPLE;
D O I
10.1214/ECP.v20-4315
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We study the large deviation rate functional for the empirical distribution of independent Brownian particles with drift. In one dimension, it has been shown by Adams, Dirr, Peletier and Zimmer that this functional is asymptotically equivalent (in the sense of Gamma-convergence as the time-step goes to zero) to the Jordan-Kinderlehrer-Otto functional arising in the Wasserstein gradient flow structure of the Fokker-Planck equation. In higher dimensions, part of this statement (the lower bound) has been recently proved by Duong, Laschos and Renger, but the upper bound remained open, since their proof of the upper bound relies on regularity properties of optimal transport maps that are restricted to one dimension. In this note we present a new proof of the upper bound, thereby generalising the result of Adams, Dirr, Peletier and Zimmer to arbitrary dimensions.
引用
收藏
页码:1 / 12
页数:12
相关论文
共 50 条
  • [1] WASSERSTEIN GRADIENT FLOWS FROM LARGE DEVIATIONS OF MANY-PARTICLE LIMITS
    Manh Hong Duong
    Laschos, Vaios
    Renger, Michiel
    ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS, 2013, 19 (04) : 1166 - 1188
  • [2] Large deviations and gradient flows
    Adams, Stefan
    Dirr, Nicolas
    Peletier, Mark
    Zimmer, Johannes
    PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2013, 371 (2005):
  • [3] From a Large-Deviations Principle to the Wasserstein Gradient Flow: A New Micro-Macro Passage
    Stefan Adams
    Nicolas Dirr
    Mark A. Peletier
    Johannes Zimmer
    Communications in Mathematical Physics, 2011, 307 : 791 - 815
  • [4] From a Large-Deviations Principle to the Wasserstein Gradient Flow: A New Micro-Macro Passage
    Adams, Stefan
    Dirr, Nicolas
    Peletier, Mark A.
    Zimmer, Johannes
    COMMUNICATIONS IN MATHEMATICAL PHYSICS, 2011, 307 (03) : 791 - 815
  • [5] Approximate Inference with Wasserstein Gradient Flows
    Frogner, Charlie
    Poggio, Tomaso
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 2581 - 2589
  • [6] Policy Optimization as Wasserstein Gradient Flows
    Zhang, Ruiyi
    Chen, Changyou
    Li, Chunyuan
    Carin, Lawrence
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [7] Entropic Approximation of Wasserstein Gradient Flows
    Peyre, Gabriel
    SIAM JOURNAL ON IMAGING SCIENCES, 2015, 8 (04): : 2323 - 2351
  • [8] {Euclidean, metric, and Wasserstein} gradient flows: an overview
    Santambrogio, Filippo
    BULLETIN OF MATHEMATICAL SCIENCES, 2017, 7 (01) : 87 - 154
  • [9] Primal Dual Methods for Wasserstein Gradient Flows
    Carrillo, Jose A.
    Craig, Katy
    Wang, Li
    Wei, Chaozhen
    FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2022, 22 (02) : 389 - 443
  • [10] Primal Dual Methods for Wasserstein Gradient Flows
    José A. Carrillo
    Katy Craig
    Li Wang
    Chaozhen Wei
    Foundations of Computational Mathematics, 2022, 22 : 389 - 443