arXiv · 2610.32339
Optimal Multiclass Online Regret with Arbitrary Label Spaces
Abstract
We determine the optimal regret in agnostic multiclass online learning with arbitrary, possibly infinite, label spaces. For every hypothesis class of multiclass Littlestone dimension $d<\infty$, we prove a regret upper bound of $O(\min\{T,\sqrt{dT}\})$ over $T$ rounds, matching the known lower bound. This resolves a question of Hanneke et al. (2023) and extends the optimal binary regret bound of Alon et al. (2021). Our proof strengthens the one-sided expert cover of Hanneke et al. (2023) to a fractional cover. We combine this cover with a minimax reduction to a finite expert game, whose best-response rewards provide the disagreement bounds needed for chaining.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Sajad Ashkezari, Shai Ben-David. 2026-10-23. Optimal Multiclass Online Regret with Arbitrary Label Spaces. https://searcharxiv.com/abs/2610.32339
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.