Manifold learning with bi-stochastic kernels

TL;DR

This paper investigates the infinitesimal generator of diffusion processes defined by bi-stochastic kernels on Riemannian manifolds, revealing how normalization affects the generator and connecting it to heat kernels, with implications for manifold learning.

Contribution

It characterizes the infinitesimal generator of bi-stochastic kernel-based diffusion processes and explores their spectral properties, extending understanding of kernel normalization in manifold learning.

Findings

Derived the infinitesimal generator dependence on data distribution and measure.

Connected bi-stochastic kernels to heat kernel in special cases.

Provided Nyström extension formulas for eigenfunction gradients.

Abstract

In this paper we answer the following question: what is the infinitesimal generator of the diffusion process defined by a kernel that is normalized such that it is bi-stochastic with respect to a specified measure? More precisely, under the assumption that data is sampled from a Riemannian manifold we determine how the resulting infinitesimal generator depends on the potentially nonuniform distribution of the sample points, and the specified measure for the bi-stochastic normalization. In a special case, we demonstrate a connection to the heat kernel. We consider both the case where only a single data set is given, and the case where a data set and a reference set are given. The spectral theory of the constructed operators is studied, and Nystr\"om extension formulas for the gradients of the eigenfunctions are computed. Applications to discrete point sets and manifold learning are discussed.