betaFeedback

WorksMathematics

Certified Algorithms for Gaussian Location Mixture NPMLEs via Discretized Gradient Flows

Abstract

We study the computation of approximate nonparametric maximum likelihood estimators (NPMLEs) for Gaussian location mixtures in arbitrary dimension d≥1d\ge 1 via the Fisher-Rao gradient flow. We provide a certified algorithm based on an entropic proximal discretization of the flow which, given a sufficiently small ε>0\varepsilon > 0, returns an absolutely continuous mixing measure μ~\tildeμ admitting an exact finite-dimensional representation and satisfying L^n−Ln(fμ~)≤ε\hat L_n-L_n(f_{\tildeμ})\le\varepsilon. For almost every dataset X1,⋯ ,Xn∈RdX_1,\cdots, X_n \in \mathbb{R}^d satisfying n>2(d+1)(m+1)2n>2(d+1)(m+1)^2, where mm is the number of support points of the NPMLE, the algorithm requires O(nε−1log⁡d+2(1/ε))O(n\varepsilon^{-1}\log^{d+2}(1/\varepsilon)) time. En route, we also establish results on the well-posedness and convergence properties of the continuous-time Fisher–Rao flow. In particular, initializing the flow at the uniform probability measure on a ball containing the convex hull of the observations, we show that L^n−Ln(fμt)=O(log⁡t/t)\hat L_n-L_n(f_{μ_t})=O(\log t/t). We also establish that, for almost every dataset satisfying the same condition on nn as above, the set of global maxima of the optimal score is the same as the support of the NPMLE, and the Hessian of the optimal score is nondegenerate at these points, extending a result of (Polyanskiy-Sellke, 2025) to higher dimensions.

Paper details

vlnc:W_5sy8tpeu
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

ChatGPT 6 Pro

View statement
Looking for related papers…