A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Orabona, Francesco
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918474636328960
author Orabona, Francesco
author_facet Orabona, Francesco
contents In Orabona and Pál [2016], we introduced the shifted KT potentials, to remove the $\ln \ln T$ factor in the parameter-free learning with expert bound. In this short technical note, I show that this is equivalent to changing the prior in the Krichevsky--Trofimov algorithm. Then, I show how to use the same idea to remove the $\ln \ln T$ factor in the data-independent bound for the Squint algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26926
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound
Orabona, Francesco
Machine Learning
Optimization and Control
In Orabona and Pál [2016], we introduced the shifted KT potentials, to remove the $\ln \ln T$ factor in the parameter-free learning with expert bound. In this short technical note, I show that this is equivalent to changing the prior in the Krichevsky--Trofimov algorithm. Then, I show how to use the same idea to remove the $\ln \ln T$ factor in the data-independent bound for the Squint algorithm.
title A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2604.26926