Guardado en:
Detalles Bibliográficos
Autores principales: Akhavan, Arya, Shidani, Amitis, Ayoub, Alex, Janz, David
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.20982
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914576754278400
author Akhavan, Arya
Shidani, Amitis
Ayoub, Alex
Janz, David
author_facet Akhavan, Arya
Shidani, Amitis
Ayoub, Alex
Janz, David
contents We introduce a dimension-free Bernstein-type tail inequality for self-normalised martingales, where the normalisation uses the predictable quadratic variation and the radius depends on the information gain of the observed covariance. As applications, we provide ellipsoidal confidence sequences for logistic regression with adaptively chosen Hilbert-valued covariates, and give instance-adaptive regret bounds for Hilbert-armed logistic bandits.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20982
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bernstein-type dimension-free concentration for self-normalised martingales
Akhavan, Arya
Shidani, Amitis
Ayoub, Alex
Janz, David
Probability
Statistics Theory
We introduce a dimension-free Bernstein-type tail inequality for self-normalised martingales, where the normalisation uses the predictable quadratic variation and the radius depends on the information gain of the observed covariance. As applications, we provide ellipsoidal confidence sequences for logistic regression with adaptively chosen Hilbert-valued covariates, and give instance-adaptive regret bounds for Hilbert-armed logistic bandits.
title Bernstein-type dimension-free concentration for self-normalised martingales
topic Probability
Statistics Theory
url https://arxiv.org/abs/2507.20982