Disintegration theorem for multifunctions, with applications to empirical Wasserstein distances and average-case statistical bounds

TL;DR

This paper generalizes the disintegration theorem for multifunctions, introduces the concept of asymptotic disintegrability, and applies it to improve statistical bounds in Wasserstein distances and empirical averages.

Contribution

It extends the disintegration theorem to multifunctions, defines asymptotic disintegrability, and demonstrates its applications in statistical convergence and empirical approximation bounds.

Findings

Asymptotically disintegrable spaces allow improved high-probability Wasserstein convergence rates.

The paper provides examples and counterexamples of asymptotic disintegrability.

High-probability bounds for empirical averages depend only on local Lipschitz constants.

Abstract

We prove a generalisation of the disintegration theorem to the setting of multifunctions between Polish probability spaces. Whereas the classical disintegration theorem guarantees the disintegration of a probability measure along the partition of the underlying space by the fibres of a measurable function, our theorem gives necessary and sufficient conditions for the measure to disintegrate along a cover of the underlying space defined by the fibres of a measurable multifunction. Building on this theorem, we introduce a new statistical notion: We declare a metric Polish probability space to be asymptotically disintegrable if $n$ i.i.d.-centred balls of decreasing radius carry a disintegration of the measure with probability tending to unity as $n\rightarrow\infty$. We give a number of both $1$-dimensional and higher-dimensional examples of asymptotically disintegrable spaces with associated quantitative rates, as well as a strong counterexample. Finally, we give two applications of the notion of asymptotic disintegrability. First, we prove that asymptotically disintegrable spaces admit an easy high-probability quantification of the law of large numbers in Wasserstein space, which in all dimensions either recovers or improves upon the best known rates in some regimes, and is never any worse than existing rates by more than a factor of 2 in the exponent of $n$, where $n$ is the number of sample points. Second, we prove that any asymptotically disintegrable space admits a high-probability bound on the error in approximating the expectation of any Lipschitz function by its empirical average over an i.i.d.\ sample. The bound is average-case in the sense that it depends only on the empirical average of the local Lipschitz constants of the function, rather than the global Lipschitz constant as obtained by Kantorovich-Rubinstein duality.