English
Related papers

Related papers: Implicit Bias of the JKO Scheme

200 papers

We introduce in this paper two time discretization schemes tailored for a range of Wasserstein gradient flows. These schemes are designed to preserve mass, positivity and to be uniquely solvable. In addition, they also ensure energy…

Numerical Analysis · Mathematics 2024-07-15 Shiheng Zhang , Jie Shen

In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While this approach also controls the distance between the posterior…

Machine Learning · Computer Science 2025-08-28 Jannis Chemseddine , Paul Hagemann , Gabriele Steidl , Christian Wald

We propose an unconditionally energy-stable, orthonormality-preserving, component-wise splitting iterative scheme for the Kohn-Sham gradient flow based model in the electronic structure calculation. We first study the scheme discretized in…

Numerical Analysis · Mathematics 2024-10-01 Xiuping Wang , Huangxin Chen , Jisheng Kou , Shuyu Sun

The proximal algorithm is a powerful tool to minimize nonlinear and nonsmooth functionals in a general metric space. Motivated by the recent progress in studying the training dynamics of the noisy gradient descent algorithm on two-layer…

Optimization and Control · Mathematics 2026-05-19 Shuailong Zhu , Xiaohui Chen

We consider flows of ordinary differential equations (ODEs) driven by path differentiable vector fields. Path differentiable functions constitute a proper subclass of Lipschitz functions which admit conservative gradients, a notion of…

Machine Learning · Computer Science 2022-01-12 Swann Marx , Edouard Pauwels

We study properties of an attractive-repulsive energy functional based on power-kernels, which can be used for halftoning of images. In the first part of this work, using a variational framework for probability measures, we examine…

Analysis of PDEs · Mathematics 2013-10-07 Jan-Christian Hütter

We study the Wasserstein gradient flow of the Sinkhorn divergence when both the source and the target are Gaussian distributions. We prove the existence of a flow that stays in the class of Gaussian distributions, and is unique in the…

Analysis of PDEs · Mathematics 2026-02-20 Mathis Hardion , Théo Lacombe

We investigate a family of gradient flows of positive and probability measures, focusing on the Hellinger-Kantorovich (HK) geometry, which unifies transport mechanism of Otto-Wasserstein, and the birth-death mechanism of Hellinger (or…

Analysis of PDEs · Mathematics 2025-01-29 Alexander Mielke , Jia-Jie Zhu

We examine the infinite-dimensional optimization problem of finding a decomposition of a probability measure into K probability sub-measures to minimize specific loss functions inspired by applications in clustering and user grouping. We…

Optimization and Control · Mathematics 2024-06-04 Jiangze Han , Christopher Thomas Ryan , Xin T. Tong

We study the long time behavior of the Wasserstein gradient flow for an energy functional consisting of two components: particles are attracted to a fixed profile $\omega$ by means of an interaction kernel $\psi_a(z)=|z|^{q_a}$,and they…

Analysis of PDEs · Mathematics 2014-01-13 Marco Di Francesco , Massimo Fornasier , Jan-Christian Hütter , Daniel Matthes

Covariate shift arises when covariate distributions differ between source and target populations while the conditional distribution of the response remains invariant, and it underlies problems in missing data and causal inference. We…

Methodology · Statistics 2026-01-13 Junjun Lang , Qiong Zhang , Yukun Liu

Recently, optimization on the Riemannian manifold have provided valuable insights to the optimization community. In this regard, extending these methods to to the Wasserstein space is of particular interest, since optimization on…

Machine Learning · Computer Science 2025-11-05 Mingyang Yi , Bohan Wang

Wasserstein distributionally robust optimization (WDRO) attempts to learn a model that minimizes the local worst-case risk in the vicinity of the empirical data distribution defined by Wasserstein ball. While WDRO has received attention as…

Machine Learning · Statistics 2020-06-23 Yongchan Kwon , Wonyoung Kim , Joong-Ho Won , Myunghee Cho Paik

Many applications in machine learning involve data represented as probability distributions. The emergence of such data requires radically novel techniques to design tractable gradient flows on probability distributions over this type of…

Machine Learning · Computer Science 2025-06-10 Clément Bonet , Christophe Vauthier , Anna Korba

The Wasserstein barycenter extends the Euclidean mean to the space of probability measures by minimizing the weighted sum of squared 2-Wasserstein distances. We develop a free-support algorithm for computing Wasserstein barycenters that…

Machine Learning · Statistics 2025-09-17 Kisung You

The Wasserstein probability metric has received much attention from the machine learning community. Unlike the Kullback-Leibler divergence, which strictly measures change in probability, the Wasserstein metric reflects the underlying…

Machine Learning · Computer Science 2017-06-01 Marc G. Bellemare , Ivo Danihelka , Will Dabney , Shakir Mohamed , Balaji Lakshminarayanan , Stephan Hoyer , Rémi Munos

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

New implicit and implicit-explicit time-stepping methods for the wave equation in second-order form are described with application to two and three-dimensional problems discretized on overset grids. The implicit schemes are single step,…

Numerical Analysis · Mathematics 2024-04-24 Allison M. Carson , Jeffrey W. Banks , William D. Henshaw , Donald W. Schwendeman

The equality between dissipation and energy drop is a structural property of gradient-flow dynamics. The classical implicit Euler scheme fails to reproduce this equality at the discrete level. We discuss two modifications of the Euler…

Numerical Analysis · Mathematics 2019-08-28 Ansgar Jüngel , Ulisse Stefanelli , Lara Trussardi

We provide attainable analytical tools to estimate the error of flow-based generative models under the Wasserstein metric and to establish the optimal sampling iteration complexity bound with respect to dimension as $O(\sqrt{d})$. We show…

Machine Learning · Computer Science 2025-12-09 Xiangjun Meng , Zhongjian Wang