Optimal Multiclass Online Regret with Arbitrary Label Spaces

2026-10-26来源 arXiv stat.MLEnglish
arXiv:2610.32339v1 Announce Type: cross 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

原文：https://www.a8q9.cn/en/article/optimal-multiclass-online-regret-with-arbitrary-label-spaces-d075e7.html

相关文章