Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Freund, Yoav, Harvey, Nicholas J. A., Portella, Victor S., Qi, Yabing, Wang, Yu-Xiang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.08151
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917258106765312
author Freund, Yoav
Harvey, Nicholas J. A.
Portella, Victor S.
Qi, Yabing
Wang, Yu-Xiang
author_facet Freund, Yoav
Harvey, Nicholas J. A.
Portella, Victor S.
Qi, Yabing
Wang, Yu-Xiang
contents We consider the problem of prediction with expert advice for ``easy'' sequences. We show that a variant of NormalHedge enjoys a second-order $ε$-quantile regret bound of $O\big(\sqrt{V_T \log(V_T/ε)}\big) $ when $V_T > \log N$, where $V_T$ is the cumulative second moment of instantaneous per-expert regret averaged with respect to a natural distribution determined by the algorithm. The algorithm is motivated by a continuous time limit using Stochastic Differential Equations. The discrete time analysis uses self-concordance techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08151
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A second order regret bound for NormalHedge
Freund, Yoav
Harvey, Nicholas J. A.
Portella, Victor S.
Qi, Yabing
Wang, Yu-Xiang
Machine Learning
We consider the problem of prediction with expert advice for ``easy'' sequences. We show that a variant of NormalHedge enjoys a second-order $ε$-quantile regret bound of $O\big(\sqrt{V_T \log(V_T/ε)}\big) $ when $V_T > \log N$, where $V_T$ is the cumulative second moment of instantaneous per-expert regret averaged with respect to a natural distribution determined by the algorithm. The algorithm is motivated by a continuous time limit using Stochastic Differential Equations. The discrete time analysis uses self-concordance techniques.
title A second order regret bound for NormalHedge
topic Machine Learning
url https://arxiv.org/abs/2602.08151