Guardado en:
Detalles Bibliográficos
Autores principales: Wee, Timothy L. H., Tatikonda, Sekhar
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2312.01248
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917158358876160
author Wee, Timothy L. H.
Tatikonda, Sekhar
author_facet Wee, Timothy L. H.
Tatikonda, Sekhar
contents A random vector whose norm and overlap (inner product with an independent copy) concentrates is shown to have random low-dimensional projections that are approximately random Gaussians. Conversely, asymptotically random Gaussian projections imply these hypotheses. This extends and unites several existing results in geometric functional analysis and spin glasses. Applications include a large-system characterization of the joint law of cavity fields in the Sherrington-Kirkpatrick model.
format Preprint
id arxiv_https___arxiv_org_abs_2312_01248
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Random projections beyond zero overlap
Wee, Timothy L. H.
Tatikonda, Sekhar
Probability
60K35, 60F05, 82B44
A random vector whose norm and overlap (inner product with an independent copy) concentrates is shown to have random low-dimensional projections that are approximately random Gaussians. Conversely, asymptotically random Gaussian projections imply these hypotheses. This extends and unites several existing results in geometric functional analysis and spin glasses. Applications include a large-system characterization of the joint law of cavity fields in the Sherrington-Kirkpatrick model.
title Random projections beyond zero overlap
topic Probability
60K35, 60F05, 82B44
url https://arxiv.org/abs/2312.01248