Enregistré dans:
Détails bibliographiques
Auteur principal: Vandermeulen, Robert A.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.21396
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915470177730560
author Vandermeulen, Robert A.
author_facet Vandermeulen, Robert A.
contents We introduce PMODE (Partitioned Mixture Of Density Estimators), a general and modular framework for mixture modeling with both parametric and nonparametric components. PMODE builds mixtures by partitioning the data and fitting separate estimators to each subset. It attains near-optimal rates for this estimator class and remains valid even when the mixture components come from different distribution families. As an application, we develop MV-PMODE, which scales a previously theoretical approach to high-dimensional density estimation to settings with thousands of dimensions. Despite its simplicity, it performs competitively against deep baselines on CIFAR-10 anomaly detection.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PMODE: Theoretically Grounded and Modular Mixture Modeling
Vandermeulen, Robert A.
Machine Learning
We introduce PMODE (Partitioned Mixture Of Density Estimators), a general and modular framework for mixture modeling with both parametric and nonparametric components. PMODE builds mixtures by partitioning the data and fitting separate estimators to each subset. It attains near-optimal rates for this estimator class and remains valid even when the mixture components come from different distribution families. As an application, we develop MV-PMODE, which scales a previously theoretical approach to high-dimensional density estimation to settings with thousands of dimensions. Despite its simplicity, it performs competitively against deep baselines on CIFAR-10 anomaly detection.
title PMODE: Theoretically Grounded and Modular Mixture Modeling
topic Machine Learning
url https://arxiv.org/abs/2508.21396