中文
相关论文

相关论文: On the total variation Wasserstein gradient flow a…

200 篇论文

We present a method to efficiently compute Wasserstein gradient flows. Our approach is based on a generalization of the back-and-forth method (BFM) introduced by Jacobs and L\'eger to solve optimal transport problems. We evolve the gradient…

数值分析 · 数学 2020-11-17 Matt Jacobs , Wonjun Lee , Flavien Léger

Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in…

机器学习 · 统计学 2024-11-01 Cheng Gao , Yuan Cao , Zihao Li , Yihan He , Mengdi Wang , Han Liu , Jason Matthew Klusowski , Jianqing Fan

In this paper, we study higher-order-accurate-in-time minimizing movements schemes for Wasserstein gradient flows. We introduce a novel accelerated second-order scheme, leveraging the differential structure of the Wasserstein space in both…

偏微分方程分析 · 数学 2025-12-23 Raymond Chu , Matt Jacobs

In this work we analyze the Total Variation-Wasserstein minimization problem. We propose an alternative form of deriving optimality conditions from the approach of Calier\&Poon'18, and as result obtain further regularity for the quantities…

偏微分方程分析 · 数学 2023-08-22 Antonin Chambolle , Vincent Duval , Joao Miguel Machado

This is the first of a series of papers devoted to a thorough analysis of the class of gradient flows in a metric space $(X,\mathsf{d})$ that can be characterized by Evolution Variational Inequalities. We present new results concerning the…

泛函分析 · 数学 2018-10-10 Matteo Muratori , Giuseppe Savaré

This study focuses on a Wasserstein-type gradient flow, which represents an optimization process of a continuous model of a Deep Neural Network (DNN). First, we establish the existence of a minimizer for an average loss of the model under…

机器学习 · 计算机科学 2024-04-16 Noboru Isobe

We show that the continuous-time gradient descent in Rn can be viewed as an optimal controlled evolution for a suitable action functional; a similar result holds for stochastic gradient descent. We then provide an analogous characterization…

最优化与控制 · 数学 2025-11-03 Yongxin Chen , Tryphon Georgiou , Michele Pavon

We study the Fokker-Planck equation as the hydrodynamic limit of a stochastic particle system on one hand and as a Wasserstein gradient flow on the other. We write the rate functional, that characterizes the large deviations from the…

偏微分方程分析 · 数学 2012-03-29 Manh Hong Duong , Vaios Laschos , Michiel Renger

We consider a Fokker-Planck equation which is coupled to an externally given time-dependent constraint on its first moment. This constraint introduces a Lagrange-multiplier which renders the equation nonlocal and nonlinear. In this paper we…

偏微分方程分析 · 数学 2018-11-28 Simon Eberle , Barbara Niethammer , André Schlichting

We study a system of drift-diffusion PDEs for a potentially infinite number of incompressible phases, subject to a joint pointwise volume constraint. Our analysis is based on the interpretation as a collection of coupled Wasserstein…

偏微分方程分析 · 数学 2024-11-22 Clément Cancès , Daniel Matthes , Ismael Medina , Bernhard Schmitzer

We introduce a novel variant of the JKO scheme to approximate Darcy's law with a pressure dependent source term. By introducing a new variable that implicitly controls the source term, our scheme is still able to use the standard…

偏微分方程分析 · 数学 2020-12-30 Matt Jacobs , Inwon Kim , Jiajun Tong

Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of…

机器学习 · 统计学 2019-05-16 Luca Ambrogioni , Umut Guclu , Marcel van Gerven

Riemannian flow matching (RFM) extends flow-based generative modeling to data supported on manifolds by learning a time-dependent tangent vector field whose flow-ODE transports a simple base distribution to the data law. We develop a…

机器学习 · 统计学 2026-02-06 Yunrui Guan , Krishnakumar Balasubramanian , Shiqian Ma

We study distributionally robust optimization (DRO) problems with uncertainty sets consisting of high-dimensional random vectors that are close in the multivariate Wasserstein distance to a reference random vector. We give conditions when…

最优化与控制 · 数学 2026-01-30 Brandon Tam , Silvana M. Pesenti

We prove the existence of nonnegative weak solutions to a class of second and fourth order nonautonomous nonlinear evolution equations with an explicitly time-dependent mobility function posed on the whole space $\mathbb{R}^d$, for…

偏微分方程分析 · 数学 2016-04-27 Jonathan Zinsl

Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable solutions by hedging against data perturbations in Wasserstein distance. Despite its recent empirical success in operations research and machine…

机器学习 · 计算机科学 2022-05-03 Rui Gao

Normalizing flow is a class of deep generative models for efficient sampling and likelihood estimation, which achieves attractive performance, particularly in high dimensions. The flow is often implemented using a sequence of invertible…

机器学习 · 统计学 2024-02-19 Chen Xu , Xiuyuan Cheng , Yao Xie

We introduce a time discretization for Wasserstein gradient flows based on the classical Backward Differentiation Formula of order two. The main building block of the scheme is the notion of geodesic extrapolation in the Wasserstein space,…

偏微分方程分析 · 数学 2023-11-20 Thomas Gallouët , Andrea Natale , Gabriele Todeschi

In this paper, we consider the convergence rate with respect to the Wasserstein distance in the invariance principle for sequential dynamical systems. We utilize and modify the techniques previously employed for stationary sequences to…

动力系统 · 数学 2024-10-29 Zhenxin Liu , Zhe Wang

The sliced-Wasserstein flow is an evolution equation where a probability density evolves in time, advected by a velocity field computed as the average among directions in the unit sphere of the optimal transport displacements from its 1D…

最优化与控制 · 数学 2024-05-13 Giacomo Cozzi , Filippo Santambogio