English
Related papers

Related papers: Scalable Wasserstein Gradient Flow for Generative …

200 papers

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 a variant of the dynamical optimal transport problem in which the energy to be minimised is modulated by the covariance matrix of the distribution. Such transport metrics arise naturally in mean-field limits of certain ensemble…

Analysis of PDEs · Mathematics 2024-12-23 Martin Burger , Matthias Erbar , Franca Hoffmann , Daniel Matthes , André Schlichting

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

Score-based generative models (SGMs) is a recent class of deep generative models with state-of-the-art performance in many applications. In this paper, we establish convergence guarantees for a general class of SGMs in 2-Wasserstein…

Machine Learning · Computer Science 2025-02-18 Xuefeng Gao , Hoang M. Nguyen , Lingjiong Zhu

Particle-based variational inference methods (ParVIs) such as Stein variational gradient descent (SVGD) update the particles based on the kernelized Wasserstein gradient flow for the Kullback-Leibler (KL) divergence. However, the design of…

Machine Learning · Statistics 2023-10-26 Ziheng Cheng , Shiyue Zhang , Longlin Yu , Cheng Zhang

Generative Adversarial Nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often not stable. While this is…

Computer Vision and Pattern Recognition · Computer Science 2018-03-30 Ishan Deshpande , Ziyu Zhang , Alexander Schwing

We construct an efficient primal-dual forward-backward (PDFB) splitting method for computing a class of minimizing movement schemes with nonlinear mobility transport distances, and apply it to computing Wasserstein-like gradient flows. This…

Numerical Analysis · Mathematics 2025-04-18 Yunhong Deng , Li Wang , Chaozhen Wei

We modify the JKO scheme, which is a time discretization of Wasserstein gradient flows, by replacing the Wasserstein distance with more general transport costs on manifolds. We show when the cost function has a mixed Hessian which defines a…

Analysis of PDEs · Mathematics 2024-02-28 Cale Rankin , Ting-Kam Leonard Wong

We propose a deterministic sampling framework using Score-Based Transport Modeling for sampling an unnormalized target density $\pi$ given only its score $\nabla \log \pi$. Our method approximates the Wasserstein gradient flow on…

Machine Learning · Computer Science 2025-10-21 Vasily Ilin , Peter Sushko , Jingwei Hu

In this paper, we propose a data-based methodology to solve a multi-period stochastic optimal water flow (OWF) problem for water distribution networks (WDNs). The framework explicitly considers the pump schedule and water network head level…

Optimization and Control · Mathematics 2022-04-26 Yi Guo , Shen Wang , Ahmad Taha , Tyler Summers

Wasserstein distributionally robust optimization (WDRO) strengthens statistical learning under model uncertainty by minimizing the local worst-case risk within a prescribed ambiguity set. Although WDRO has been extensively studied in…

Machine Learning · Statistics 2025-11-12 Changyu Liu , Yuling Jiao , Junhui Wang , Jian Huang

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le

Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs…

Machine Learning · Computer Science 2024-01-18 Yi Shen , Pan Xu , Michael M. Zavlanos

We study a discretization in space and time for a class of nonlinear diffusion equations with flux limitation. That class contains the so-called relativistic heat equation, as well as other gradient flows of Renyi entropies with respect to…

Analysis of PDEs · Mathematics 2019-10-23 Daniel Matthes , Benjamin Söllner

This paper reviews different numerical methods for specific examples of Wasserstein gradient flows: we focus on nonlinear Fokker-Planck equations,but also discuss discretizations of the parabolic-elliptic Keller-Segel model and of the…

Numerical Analysis · Mathematics 2020-03-10 Jose A. Carrillo , Daniel Matthes , Marie-Therese Wolfram

Optimal transport (OT) provides powerful tools for comparing probability measures in various types. The Wasserstein distance which arises naturally from the idea of OT is widely used in many machine learning applications. Unfortunately,…

Optimization and Control · Mathematics 2021-06-03 Shu Liu , Haodong Sun , Hongyuan Zha

With the rapidly growing model complexity and data volume, training deep generative models (DGMs) for better performance has becoming an increasingly more important challenge. Previous research on this problem has mainly focused on…

Machine Learning · Computer Science 2021-12-08 Yufan Zhou , Chunyuan Li , Changyou Chen , Jinhui Xu

We study estimation problems in safety-critical applications with streaming data. Since estimation problems can be posed as optimization problems in the probability space, we devise a stochastic projected Wasserstein gradient flow that…

Systems and Control · Electrical Eng. & Systems 2023-04-07 Nicolas Lanzetti , Efe C. Balta , Dominic Liao-McPherson , Florian Dörfler

In federated learning, participating clients typically possess non-i.i.d. data, posing a significant challenge to generalization to unseen distributions. To address this, we propose a Wasserstein distributionally robust optimization scheme…

Machine Learning · Computer Science 2022-06-06 Tung-Anh Nguyen , Tuan Dung Nguyen , Long Tan Le , Canh T. Dinh , Nguyen H. Tran

Turbulent flows are chaotic and unsteady, but their statistical distribution converges to a statistical steady state. Engineering quantities of interest typically take the form of time-average statistics such as $ \frac{1}{t} \int_0^t f (…

Fluid Dynamics · Physics 2025-09-17 Tom Hickling , Jonathan F. MacArt , Justin Sirignano , Den Waidmann