Fast computation and theoretical guarantees for the NPMLE in exponential family mixtures

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Zhang, Yan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914496418676736
author Zhang, Yan
author_facet Zhang, Yan
contents This work makes two advances in the study of the (approximate) nonparametric maximum likelihood estimator (NPMLE) for exponential family mixture models. First, we develop a data-compression strategy that reduces the cost of repeated likelihood evaluations in NPMLE computation to logarithmic order in the sample size. Second, we show that, for a broad class of approximate NPMLEs, the resulting marginal density estimator attains an almost parametric rate of convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19725
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fast computation and theoretical guarantees for the NPMLE in exponential family mixtures
Zhang, Yan
Statistics Theory
Computation
This work makes two advances in the study of the (approximate) nonparametric maximum likelihood estimator (NPMLE) for exponential family mixture models. First, we develop a data-compression strategy that reduces the cost of repeated likelihood evaluations in NPMLE computation to logarithmic order in the sample size. Second, we show that, for a broad class of approximate NPMLEs, the resulting marginal density estimator attains an almost parametric rate of convergence.
title Fast computation and theoretical guarantees for the NPMLE in exponential family mixtures
topic Statistics Theory
Computation
url https://arxiv.org/abs/2604.19725