Guardado en:
Detalles Bibliográficos
Autores principales: Devroye, Luc, Lugosi, Gabor, Zwiernik, Piotr
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2408.15624
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916888753209344
author Devroye, Luc
Lugosi, Gabor
Zwiernik, Piotr
author_facet Devroye, Luc
Lugosi, Gabor
Zwiernik, Piotr
contents We consider the problem of structure recovery in a graphical model of a tree where some variables are latent. Specifically, we focus on the Gaussian case, which can be reformulated as a well-studied problem: recovering a semi-labeled tree from a distance metric. We introduce randomized procedures that achieve query complexity of optimal order. Additionally, we provide statistical analysis for scenarios where the tree distances are noisy. The Gaussian setting can be extended to other situations, including the binary case and non-paranormal distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15624
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning latent tree models with small query complexity
Devroye, Luc
Lugosi, Gabor
Zwiernik, Piotr
Statistics Theory
62H22
We consider the problem of structure recovery in a graphical model of a tree where some variables are latent. Specifically, we focus on the Gaussian case, which can be reformulated as a well-studied problem: recovering a semi-labeled tree from a distance metric. We introduce randomized procedures that achieve query complexity of optimal order. Additionally, we provide statistical analysis for scenarios where the tree distances are noisy. The Gaussian setting can be extended to other situations, including the binary case and non-paranormal distributions.
title Learning latent tree models with small query complexity
topic Statistics Theory
62H22
url https://arxiv.org/abs/2408.15624