Self-regularizing Property of Nonparametric Maximum Likelihood Estimator in Mixture Models

Abstract

Introduced by Kiefer and Wolfowitz \cite{KW56}, the nonparametric maximum likelihood estimator (NPMLE) is a widely used methodology for learning mixture odels and empirical Bayes estimation. Sidestepping the non-convexity in mixture likelihood, the NPMLE estimates the mixing distribution by maximizing the total likelihood over the space of probability measures, which can be viewed as an extreme form of overparameterization. In this paper we discover a surprising property of the NPMLE solution. Consider, for example, a Gaussian mixture model on the real line with a subgaussian mixing distribution. Leveraging complex-analytic techniques, we show that with high probability the NPMLE based on a sample of size $n$ has $O(\log n)$ atoms (mass points), significantly improving the deterministic upper bound of $n$ due to Lindsay \cite{lindsay1983geometry1}. Notably, any such Gaussian mixture is statistically indistinguishable from a finite one with $O(\log n)$ components (and this is tight for certain mixtures). Thus, absent any explicit form of model selection, NPMLE automatically chooses the right model complexity, a property we term \emph{self-regularization}. Extensions to other exponential families are given. As a statistical application, we show that this structural property can be harnessed to bootstrap existing Hellinger risk bound of the (parametric) MLE for finite Gaussian mixtures to the NPMLE for general Gaussian mixtures, recovering a result of Zhang \cite{zhang2009generalized}.

Refer conjecture of [DYPS20] in Sec 5.4 to the arxiv version arXiv:1901.03264v4

References in corpus (5)

• General maximum likelihood empirical Bayes estimation of normal means
• Estimating a Polya frequency function_2
• Optimality of Maximum Likelihood for Log-Concave Density Estimation and Bounded Convex Regression
• Optimal estimation of Gaussian mixtures via denoised method of moments
• Note on approximating the Laplace transform of a Gaussian on a complex disk

Cited by in corpus (7)

• Local Minima Structures in Gaussian Mixture Models
• Interval censored recursive forests
• Fisher-Pitman permutation tests based on nonparametric Poisson mixtures with application to single cell genomics
• Empirical Bayes PCA in high dimensions
• Multivariate, Heteroscedastic Empirical Bayes via Nonparametric Maximum Likelihood
• Note on approximating the Laplace transform of a Gaussian on a complex disk
• A Nonparametric Maximum Likelihood Approach to Mixture of Regression