Saved in:
Bibliographic Details
Main Authors: Freund, Yoav, Harvey, Nicholas J. A., Portella, Victor S., Qi, Yabing, Wang, Yu-Xiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.08151
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of 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.