Multiperiodic Processes: Ergodic Sources with a Sublinear Entropy

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Dębowski, Łukasz
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914263845568512
author Dębowski, Łukasz
author_facet Dębowski, Łukasz
contents We construct multiperiodic processes -- a simple example of stationary ergodic (but not mixing) processes over natural numbers that enjoy the vanishing entropy rate under a mild condition. Multiperiodic processes are supported on randomly shifted deterministic sequences called multiperiodic sequences, which can be efficiently generated using an algorithm called the Infinite Clock. Under a suitable parameterization, multiperiodic sequences exhibit relative frequencies of particular numbers given by Zipf's law. Exactly in the same setting, the respective multiperiodic processes satisfy an asymptotic power-law growth of block entropy, called Hilberg's law. Hilberg's law is deemed to hold for statistical language models, in particular.
format Preprint
id arxiv_https___arxiv_org_abs_2302_09049
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multiperiodic Processes: Ergodic Sources with a Sublinear Entropy
Dębowski, Łukasz
Information Theory
Machine Learning
Statistics Theory
60G10 (Primary) 62M20, 94A17 (Secondary)
We construct multiperiodic processes -- a simple example of stationary ergodic (but not mixing) processes over natural numbers that enjoy the vanishing entropy rate under a mild condition. Multiperiodic processes are supported on randomly shifted deterministic sequences called multiperiodic sequences, which can be efficiently generated using an algorithm called the Infinite Clock. Under a suitable parameterization, multiperiodic sequences exhibit relative frequencies of particular numbers given by Zipf's law. Exactly in the same setting, the respective multiperiodic processes satisfy an asymptotic power-law growth of block entropy, called Hilberg's law. Hilberg's law is deemed to hold for statistical language models, in particular.
title Multiperiodic Processes: Ergodic Sources with a Sublinear Entropy
topic Information Theory
Machine Learning
Statistics Theory
60G10 (Primary) 62M20, 94A17 (Secondary)
url https://arxiv.org/abs/2302.09049