Convergence Rates for Latent Mixing Measures in Infinite Homoscedastic Location-Scale Mixture Models

TL;DR

This paper establishes new theoretical convergence rates for latent mixing measures in infinite homoscedastic location-scale mixture models, addressing a previously open problem.

Contribution

It derives novel bounds linking mixture density convergence to discrepancies in mixing measures and scale matrices, using Wasserstein distances and PDE techniques.

Findings

Established first contraction rates for latent mixing measures in Dirichlet process mixtures with unknown scales.

Derived bounds that distinguish convergence behaviors of location and scale parameters.

Applied results to Gaussian, Cauchy, and Laplace mixture models.

Abstract

We study posterior contraction rates for mixing measures in homoscedastic location-scale mixture models with infinitely many components. While posterior convergence at the level of densities is well understood, ensuring convergence of the latent mixing measure is more challenging and has remained an open problem in settings where both location and scale parameters are unknown. We address this by deriving novel lower-bounds that connect the $L^1$ distance between mixture densities to discrepancies, based on the Wasserstein distances and the operator norm, between the underlying mixing measures and scale matrices. Our approach combines the dual formulation of the $W_1$ distance with functional-analytic approximation techniques. This leads to general inequalities, whose strength is determined (i) by the smoothness of the mixture kernel via the rate of decay of its characteristic function, and (ii) by a key lower-bound on the $L^1$ metric involving the operator norm discrepancy between scale parameters. Moreover, a novel PDE inversion condition yields a sharper inequality for important ordinary-smooth cases. We specialize these bounds to popular mixtures based on multivariate Gaussian, Cauchy, and Laplace kernels. As a consequence, we obtain first-of-their-kind contraction rates in the context of Dirichlet process mixtures with an unknown scale parameter shared across components. As a byproduct of our inequalities, we can distinguish the convergence behavior of the location mixing measure from that of the scale parameter across a range of kernel choices, leading to nuanced insights into their respective rates.