Density of compressible types and some consequences

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bays, Martin, Kaplan, Itay, Simon, Pierre
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915904446529536
author Bays, Martin
Kaplan, Itay
Simon, Pierre
author_facet Bays, Martin
Kaplan, Itay
Simon, Pierre
contents We study compressible types in the context of (local and global) NIP. By extending a result in machine learning theory (the existence of a bound on the recursive teaching dimension), we prove density of compressible types. Using this, we obtain explicit uniform honest definitions for NIP formulas (answering a question of Eshel and the second author), and build compressible models in countable NIP theories.
format Preprint
id arxiv_https___arxiv_org_abs_2107_05197
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Density of compressible types and some consequences
Bays, Martin
Kaplan, Itay
Simon, Pierre
Logic
03C45 (Primary) 03C95, 03C50 (Secondary)
We study compressible types in the context of (local and global) NIP. By extending a result in machine learning theory (the existence of a bound on the recursive teaching dimension), we prove density of compressible types. Using this, we obtain explicit uniform honest definitions for NIP formulas (answering a question of Eshel and the second author), and build compressible models in countable NIP theories.
title Density of compressible types and some consequences
topic Logic
03C45 (Primary) 03C95, 03C50 (Secondary)
url https://arxiv.org/abs/2107.05197