Semi-Nonparametric Estimation of Distribution Divergence in Non-Euclidean Spaces

TL;DR

This paper introduces a novel semi-nonparametric approach for estimating distribution divergence measures in non-Euclidean spaces using RKHS-based witness functions, addressing the challenge of unknown homeomorphisms.

Contribution

It proposes a new method leveraging learnable parametric functions and universal kernels to estimate divergence measures in non-Euclidean spaces without requiring explicit homeomorphism knowledge.

Findings

Estimators are asymptotically consistent.

Method effectively handles unknown homeomorphisms.

Provides detailed statistical analysis and practical implementation insights.

Abstract

This paper explores methods for estimating or approximating the total variation distance and the chi-squared divergence of probability measures within topological sample spaces, using independent and identically distributed samples. Our focus is on the practical scenario where the sample space is homeomorphic to subsets of Euclidean space, with the specific homeomorphism remaining unknown. Our proposed methods rely on the integral probability metric with witness functions in universal reproducing kernel Hilbert spaces (RKHSs). The estimators we develop consist of learnable parametric functions mapping the sample space to Euclidean space, paired with universal kernels defined in Euclidean space. This approach effectively overcomes the challenge of constructing universal kernels directly on non-Euclidean spaces. Furthermore, the estimators we devise demonstrate asymptotic consistency, and we provide a detailed statistical analysis, shedding light on their practical implementation.