Saved in:
Bibliographic Details
Main Authors: Rux, Nicolaj, Quellmalz, Michael, Steidl, Gabriele
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.07820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918165652439040
author Rux, Nicolaj
Quellmalz, Michael
Steidl, Gabriele
author_facet Rux, Nicolaj
Quellmalz, Michael
Steidl, Gabriele
contents Negative distance kernels $K(x,y) := - \|x-y\|$ were used in the definition of maximum mean discrepancies (MMDs) in statistics and lead to favorable numerical results in various applications. In particular, so-called slicing techniques for handling high-dimensional kernel summations profit from the simple parameter-free structure of the distance kernel. However, due to its non-smoothness in $x=y$, most of the classical theoretical results, e.g. on Wasserstein gradient flows of the corresponding MMD functional do not longer hold true. In this paper, we propose a new kernel which keeps the favorable properties of the negative distance kernel as being conditionally positive definite of order one with a nearly linear increase towards infinity and a simple slicing structure, but is Lipschitz differentiable now. Our construction is based on a simple 1D smoothing procedure of the absolute value function followed by a Riemann-Liouville fractional integral transform. Numerical results demonstrate that the new kernel performs similarly well as the negative distance kernel in gradient descent methods, but now with theoretical guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07820
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Smoothed Distance Kernels for MMDs and Applications in Wasserstein Gradient Flows
Rux, Nicolaj
Quellmalz, Michael
Steidl, Gabriele
Machine Learning
Functional Analysis
Probability
Negative distance kernels $K(x,y) := - \|x-y\|$ were used in the definition of maximum mean discrepancies (MMDs) in statistics and lead to favorable numerical results in various applications. In particular, so-called slicing techniques for handling high-dimensional kernel summations profit from the simple parameter-free structure of the distance kernel. However, due to its non-smoothness in $x=y$, most of the classical theoretical results, e.g. on Wasserstein gradient flows of the corresponding MMD functional do not longer hold true. In this paper, we propose a new kernel which keeps the favorable properties of the negative distance kernel as being conditionally positive definite of order one with a nearly linear increase towards infinity and a simple slicing structure, but is Lipschitz differentiable now. Our construction is based on a simple 1D smoothing procedure of the absolute value function followed by a Riemann-Liouville fractional integral transform. Numerical results demonstrate that the new kernel performs similarly well as the negative distance kernel in gradient descent methods, but now with theoretical guarantees.
title Smoothed Distance Kernels for MMDs and Applications in Wasserstein Gradient Flows
topic Machine Learning
Functional Analysis
Probability
url https://arxiv.org/abs/2504.07820