Quotient EM under Misspecification:Tight Local Rates and Finite-Sample Bounds in General Integral Probability Metrics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Mallik, Koustav
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911352376786944
author Mallik, Koustav
author_facet Mallik, Koustav
contents We study the expectation-maximization (EM) algorithm for general latent-variable models under (i) distributional misspecification and (ii) nonidentifiability induced by a group action. We formulate EM on the quotient parameter space and measure error using an arbitrary integral probability metric (IPM). Our main results give (a) a sharp local linear convergence rate for population EM governed by the spectral radius of the linearization on a local slice, and (b) tight finite-sample bounds for sample EM obtained via perturbed contraction inequalities and generic chaining/entropy control of EM-induced empirical processes.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01051
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quotient EM under Misspecification:Tight Local Rates and Finite-Sample Bounds in General Integral Probability Metrics
Mallik, Koustav
Statistics Theory
Methodology
We study the expectation-maximization (EM) algorithm for general latent-variable models under (i) distributional misspecification and (ii) nonidentifiability induced by a group action. We formulate EM on the quotient parameter space and measure error using an arbitrary integral probability metric (IPM). Our main results give (a) a sharp local linear convergence rate for population EM governed by the spectral radius of the linearization on a local slice, and (b) tight finite-sample bounds for sample EM obtained via perturbed contraction inequalities and generic chaining/entropy control of EM-induced empirical processes.
title Quotient EM under Misspecification:Tight Local Rates and Finite-Sample Bounds in General Integral Probability Metrics
topic Statistics Theory
Methodology
url https://arxiv.org/abs/2601.01051