A Short Note on a Variant of the Squint Algorithm
Machine Learning
2026-03-05 v1
Abstract
This short note describes a simple variant of the Squint algorithm of Koolen and Van Erven [2015] for the classic expert problem. Via an equally simple modification of their proof, we prove that this variant ensures a regret bound that resembles the one shown in a recent work by Freund et al. [2026] for a variant of the NormalHedge algorithm [Chaudhuri et al., 2009].
Cite
@article{arxiv.2603.03409,
title = {A Short Note on a Variant of the Squint Algorithm},
author = {Haipeng Luo},
journal= {arXiv preprint arXiv:2603.03409},
year = {2026}
}