Sharp mean-field analysis of permutation mixtures and permutation-invariant decisions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liang, Yiguo, Han, Yanjun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916951081615360
author Liang, Yiguo
Han, Yanjun
author_facet Liang, Yiguo
Han, Yanjun
contents We develop sharp bounds on the statistical distance between high-dimensional permutation mixtures and their i.i.d. counterparts. Our approach establishes a new geometric link between the spectrum of a complex channel overlap matrix and the information geometry of the channel, yielding tight dimension-independent bounds that close gaps left by previous work. Within this geometric framework, we also derive dimension-dependent bounds that uncover phase transitions in dimensionality for Gaussian and Poisson families. Applied to compound decision problems, this refined control of permutation mixtures enables sharper mean-field analyses of permutation-invariant decision rules, yielding strong non-asymptotic equivalence results between two notions of compound regret in Gaussian and Poisson models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12584
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sharp mean-field analysis of permutation mixtures and permutation-invariant decisions
Liang, Yiguo
Han, Yanjun
Statistics Theory
Information Theory
We develop sharp bounds on the statistical distance between high-dimensional permutation mixtures and their i.i.d. counterparts. Our approach establishes a new geometric link between the spectrum of a complex channel overlap matrix and the information geometry of the channel, yielding tight dimension-independent bounds that close gaps left by previous work. Within this geometric framework, we also derive dimension-dependent bounds that uncover phase transitions in dimensionality for Gaussian and Poisson families. Applied to compound decision problems, this refined control of permutation mixtures enables sharper mean-field analyses of permutation-invariant decision rules, yielding strong non-asymptotic equivalence results between two notions of compound regret in Gaussian and Poisson models.
title Sharp mean-field analysis of permutation mixtures and permutation-invariant decisions
topic Statistics Theory
Information Theory
url https://arxiv.org/abs/2509.12584