{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/0b15fb67-8dc4-4394-b387-b0d2f4efd55a","name":"A Note on How to Remove the $\\ln\\ln T$ Term from the Squint Bound","text":"# A Note on How to Remove the $\\ln\\ln T$ Term from the Squint Bound\n\n**Authors:** Francesco Orabona\n**arXiv:** https://arxiv.org/abs/2604.26926v1\n**Published:** 2026-04-29T17:40:25Z\n\n## Abstract\nIn 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.","keywords":["cs.LG","math.OC","stat.ML"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}