English
Related papers

Related papers: Neural Wasserstein Gradient Flows for Maximum Mean…

200 papers

We present a novel approximate inference method for diffusion processes, based on the Wasserstein gradient flow formulation of the diffusion. In this formulation, the time-dependent density of the diffusion is derived as the limit of…

Machine Learning · Statistics 2018-06-13 Charlie Frogner , Tomaso Poggio

The Stein Variational Gradient Descent (SVGD) algorithm is a deterministic particle method for sampling. However, a mean-field analysis reveals that the gradient flow corresponding to the SVGD algorithm (i.e., the Stein Variational Gradient…

Machine Learning · Statistics 2024-05-10 Ye He , Krishnakumar Balasubramanian , Bharath K. Sriperumbudur , Jianfeng Lu

We introduce the observable Wasserstein distance, a framework for deriving lower bounds on the Wasserstein distance between probability measures on Polish metric spaces, designed to bypass the computational intractability of exact optimal…

Metric Geometry · Mathematics 2026-05-12 Edivaldo Lopes dos Santos , Leandro Vicente Mauri , Washington Mio , Tom Needham

Otto's (2001) Wasserstein gradient flow of the exclusive KL divergence functional provides a powerful and mathematically principled perspective for analyzing learning and inference algorithms. In contrast, algorithms for the inclusive KL…

Machine Learning · Statistics 2024-11-04 Jia-Jie Zhu

The Wasserstein space of probability measures is known for its intricate Riemannian structure, which underpins the Wasserstein geometry and enables gradient flow algorithms. However, the Wasserstein geometry may not be suitable for certain…

Analysis of PDEs · Mathematics 2025-05-23 Zhengxin Zhang , Ziv Goldfeld , Kristjan Greenewald , Youssef Mroueh , Bharath K. Sriperumbudur

This paper aims at computing the capacity-distortion-cost (CDC) function for continuous memoryless channels, which is defined as the supremum of the mutual information between channel input and output, constrained by an input cost and an…

Information Theory · Computer Science 2025-04-30 Xinyang Li , Ziyou Tang , Vlad C. Andrei , Ullrich J. Mönich , Fan Liu , Holger Boche

Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integration. Several authors have proposed to select points by minimising a maximum mean discrepancy (MMD),…

Machine Learning · Statistics 2026-05-13 Zonghao Chen , Toni Karvonen , Heishiro Kanagawa , François-Xavier Briol , Chris. J. Oates

This contribution presents substantial computational advancements to compare measures even with varying masses. Specifically, we utilize the nonequispaced fast Fourier transform to accelerate the radial kernel convolution in unbalanced…

Optimization and Control · Mathematics 2024-05-15 Rajmadan Lakshmanan , Alois Pichler

Optimal transport is a notoriously difficult problem to solve numerically, with current approaches often remaining intractable for very large scale applications such as those encountered in machine learning. Wasserstein barycenters -- the…

Machine Learning · Computer Science 2021-02-25 Julien Lacombe , Julie Digne , Nicolas Courty , Nicolas Bonneel

We develop a fast and scalable numerical approach to solve Wasserstein gradient flows (WGFs), particularly suitable for high-dimensional cases. Our approach is to use general reduced-order models, like deep neural networks, to parameterize…

Numerical Analysis · Mathematics 2024-05-24 Yijie Jin , Shu Liu , Hao Wu , Xiaojing Ye , Haomin Zhou

Normalizing flows are a class of flexible deep generative models that offer easy likelihood computation. Despite their empirical success, there is little theoretical understanding of their expressiveness. In this work, we study residual…

Machine Learning · Computer Science 2021-06-28 Zhifeng Kong , Kamalika Chaudhuri

Recent results have shown that for two-layer fully connected neural networks, gradient flow converges to a global optimum in the infinite width limit, by making a connection between the mean field dynamics and the Wasserstein gradient flow.…

Optimization and Control · Mathematics 2020-07-16 Walid Krichene , Kenneth F. Caluya , Abhishek Halder

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Jiqing Wu , Zhiwu Huang , Dinesh Acharya , Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2019-04-17 Jiqing Wu , Zhiwu Huang , Dinesh Acharya , Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool

Optimal transport (OT) offers a versatile framework to compare complex data distributions in a geometrically meaningful way. Traditional methods for computing the Wasserstein distance and geodesic between probability measures require…

Machine Learning · Computer Science 2024-05-24 Andrew Gracyk , Xiaohui Chen

While theoretically appealing, the application of the Wasserstein distance to large-scale machine learning problems has been hampered by its prohibitive computational cost. The sliced Wasserstein distance and its variants improve the…

Machine Learning · Computer Science 2022-03-18 Xiongjie Chen , Yongxin Yang , Yunpeng Li

We address the problem of efficiently computing Wasserstein distances for multiple pairs of distributions drawn from a meta-distribution. To this end, we propose a fast estimation method based on regressing Wasserstein distance on sliced…

Machine Learning · Statistics 2026-03-04 Khai Nguyen , Hai Nguyen , Nhat Ho

We study the Wasserstein natural gradient in parametric statistical models with continuous sample spaces. Our approach is to pull back the $L^2$-Wasserstein metric tensor in the probability density space to a parameter space, equipping the…

Optimization and Control · Mathematics 2024-08-20 Yifan Chen , Wuchen Li

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…

Machine Learning · Statistics 2024-11-01 Cheng Gao , Yuan Cao , Zihao Li , Yihan He , Mengdi Wang , Han Liu , Jason Matthew Klusowski , Jianqing Fan

Over the last 25 years, techniques based on drift and minorization (d&m) have been mainstays in the convergence analysis of MCMC algorithms. However, results presented herein suggest that d&m may be less useful in the emerging area of…

Statistics Theory · Mathematics 2020-10-15 Qian Qin , James P. Hobert