中文
相关论文

相关论文: Smoothed Distance Kernels for MMDs and Application…

200 篇论文

We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modeling. This MMD, which is also known as energy distance, has several advantageous…

Maximum mean discrepancy (MMD) flows suffer from high computational costs in large scale computations. In this paper, we show that MMD flows with Riesz kernels $K(x,y) = - \|x-y\|^r$, $r \in (0,2)$ have exceptional properties which allow…

机器学习 · 计算机科学 2024-02-21 Johannes Hertrich , Christian Wald , Fabian Altekrüger , Paul Hagemann

We consider Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals $\text{MMD}_K^2(\cdot, \nu)$ for positive and negative distance kernels $K(x,y) := \pm |x-y|$ and given target measures $\nu$ on $\mathbb{R}$. Since in one…

偏微分方程分析 · 数学 2025-05-06 Richard Duong , Nicolaj Rux , Viktor Stein , Gabriele Steidl

Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions. The recent developments on…

机器学习 · 计算机科学 2015-11-11 Soheil Kolouri , Yang Zou , Gustavo K. Rohde

We give a comprehensive description of Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals $\mathcal F_\nu := \text{MMD}_K^2(\cdot, \nu)$ towards given target measures $\nu$ on the real line, where we focus on the…

偏微分方程分析 · 数学 2025-12-05 Richard Duong , Viktor Stein , Robert Beinert , Johannes Hertrich , Gabriele Steidl

Optimal transport has been very successful for various machine learning tasks; however, it is known to suffer from the curse of dimensionality. Hence, dimensionality reduction is desirable when applied to high-dimensional data with…

机器学习 · 统计学 2025-07-21 Jie Wang , March Boedihardjo , Yao Xie

Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure as singular measures can become absolutely continuous ones and conversely. In this paper we contribute to the…

机器学习 · 计算机科学 2024-03-22 Fabian Altekrüger , Johannes Hertrich , Gabriele Steidl

Maximum mean discrepancies (MMDs) like the kernel Stein discrepancy (KSD) have grown central to a wide range of applications, including hypothesis testing, sampler selection, distribution approximation, and variational inference. In each…

机器学习 · 统计学 2025-03-26 Alessandro Barp , Carl-Johann Simon-Gabriel , Mark Girolami , Lester Mackey

We construct a Wasserstein gradient flow of the maximum mean discrepancy (MMD) and study its convergence properties. The MMD is an integral probability metric defined for a reproducing kernel Hilbert space (RKHS), and serves as a metric on…

机器学习 · 统计学 2019-12-04 Michael Arbel , Anna Korba , Adil Salim , Arthur Gretton

Embedding probability distributions into reproducing kernel Hilbert spaces (RKHS) has enabled powerful nonparametric methods such as the maximum mean discrepancy (MMD), a statistical distance with strong theoretical and computational…

机器学习 · 统计学 2025-05-28 Masha Naslidnyk , Siu Lun Chau , François-Xavier Briol , Krikamol Muandet

The Wasserstein distance is a powerful metric based on the theory of optimal transport. It gives a natural measure of the distance between two distributions with a wide range of applications. In contrast to a number of the common…

机器学习 · 计算机科学 2021-02-16 Jung Hun Oh , Maryam Pouryahya , Aditi Iyer , Aditya P. Apte , Allen Tannenbaum , Joseph O. Deasy

The maximum mean discrepancy and Wasserstein distance are popular distance measures between distributions and play important roles in many machine learning problems such as metric learning, generative modeling, domain adaption, and…

机器学习 · 计算机科学 2025-01-22 Dong Qiao , Jicong Fan

Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances between probability distributions that have attracted abundant…

机器学习 · 统计学 2023-06-01 Titouan Vayer , Rémi Gribonval

The kernel Maximum Mean Discrepancy~(MMD) is a popular multivariate distance metric between distributions that has found utility in two-sample testing. The usual kernel-MMD test statistic is a degenerate U-statistic under the null, and thus…

统计方法学 · 统计学 2025-09-16 Shubhanshu Shekhar , Ilmun Kim , Aaditya Ramdas

We study the quantitative convergence of Wasserstein gradient flows of Kernel Mean Discrepancy (KMD) (also known as Maximum Mean Discrepancy (MMD)) functionals. Our setting covers in particular the training dynamics of shallow neural…

偏微分方程分析 · 数学 2026-03-03 Lénaïc Chizat , Maria Colombo , Roberto Colombo , Xavier Fernández-Real

Distances between probability distributions are a key component of many statistical machine learning tasks, from two-sample testing to generative modeling, among others. We introduce a novel distance between measures that compares them…

机器学习 · 统计学 2025-07-09 Arturo Castellanos , Anna Korba , Pavlo Mozharovskyi , Hicham Janati

In the context of kernel methods, the similarity between data points is encoded by the kernel function which is often defined thanks to the Euclidean distance, a common example being the squared exponential kernel. Recently, other distances…

机器学习 · 计算机科学 2020-02-06 Henri De Plaen , Michaël Fanuel , Johan A. K. Suykens

The paper introduces a new kernel-based Maximum Mean Discrepancy (MMD) statistic for measuring the distance between two distributions given finitely-many multivariate samples. When the distributions are locally low-dimensional, the proposed…

机器学习 · 统计学 2018-09-03 Xiuyuan Cheng , Alexander Cloninger , Ronald R. Coifman

Persistence diagrams (PDs) play a key role in topological data analysis (TDA), in which they are routinely used to describe topological properties of complicated shapes. PDs enjoy strong stability properties and have proven their utility in…

计算几何 · 计算机科学 2017-11-10 Mathieu Carrière , Marco Cuturi , Steve Oudot

Representing, comparing, and measuring the distance between probability distributions is a key task in computational statistics and machine learning. The choice of representation and the associated distance determine properties of the…

机器学习 · 统计学 2026-02-26 Masha Naslidnyk
‹ 上一页 1 2 3 10 下一页 ›