Abstract: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.
| Subjects: | Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML) |
| Cite as: | arXiv:2604.26926 [cs.LG] |
| (or arXiv:2604.26926v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26926 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Francesco Orabona [view email]
[v1]
Wed, 29 Apr 2026 17:40:25 UTC (6 KB)