Kaydedildi:
Detaylı Bibliyografya
Yazar: Aryan, Farzad
Materyal Türü: Preprint
Baskı/Yayın Bilgisi: 2025
Konular:
Online Erişim:https://arxiv.org/abs/2508.03633
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!
_version_ 1866913976507432960
author Aryan, Farzad
author_facet Aryan, Farzad
contents We study the problem of learning Gaussian Mixture Models (GMMs) and ask: which structural properties govern their sample complexity? Prior work has largely tied this complexity to the minimum pairwise separation between components, but we demonstrate this view is incomplete. We introduce the \emph{Pair Correlation Factor} (PCF), a geometric quantity capturing the clustering of component means. Unlike the minimum gap, the PCF more accurately dictates the difficulty of parameter recovery. In the uniform spherical case, we give an algorithm with improved sample complexity bounds, showing when more than the usual $ε^{-2}$ samples are necessary.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03633
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pair Correlation Factor and the Sample Complexity of Gaussian Mixtures
Aryan, Farzad
Machine Learning
62H30, 68T05, 62F12, 68Q32
I.2.6; G.3
We study the problem of learning Gaussian Mixture Models (GMMs) and ask: which structural properties govern their sample complexity? Prior work has largely tied this complexity to the minimum pairwise separation between components, but we demonstrate this view is incomplete. We introduce the \emph{Pair Correlation Factor} (PCF), a geometric quantity capturing the clustering of component means. Unlike the minimum gap, the PCF more accurately dictates the difficulty of parameter recovery. In the uniform spherical case, we give an algorithm with improved sample complexity bounds, showing when more than the usual $ε^{-2}$ samples are necessary.
title Pair Correlation Factor and the Sample Complexity of Gaussian Mixtures
topic Machine Learning
62H30, 68T05, 62F12, 68Q32
I.2.6; G.3
url https://arxiv.org/abs/2508.03633