When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses

Antoine Moulin, Emmanuel Esposito, Dirk van der Hoeven

Keywords: adaptive algorithms, regret minimization, heavy tails, prediction with expert advice

TL;DR: We provide improved adaptive expert algorithms that avoid a \sqrt{KT} term in prior regret guarantees.

Abstract: We consider the problem setting of prediction with expert advice with possibly heavy-tailed losses, i.e.\ the only assumption on the losses is an upper bound on their second moments, denoted by $\theta$. We develop adaptive algorithms that do not require any prior knowledge about the range or the second moment of the losses. Existing adaptive algorithms have what is typically considered a lower-order term in their regret guarantees. We show that this lower-order term, which is often the maximum of the losses, can actually dominate the regret bound in our setting. Specifically, we show that even with small constant $\theta$, this lower-order term can scale as $\sqrt{KT}$, where $K$ is the number of experts and $T$ is the time horizon. We propose adaptive algorithms with improved regret bounds that avoid the dependence on such a lower-order term and guarantee $\mathcal{O}(\sqrt{\theta T\log(K)})$ regret in the worst case, and $\mathcal{O}(\theta \log(KT)/\Delta_{\min})$ regret when the losses are sampled i.i.d.\ from some fixed distribution, where $\Delta_{\min}$ is the difference between the mean losses of the second best expert and the best expert. Additionally, when the loss function is the squared loss, our algorithm also guarantees improved regret bounds over prior results.

Confirmation: I understand that authors of each paper submitted to EWRL may be asked to review 2-3 other submissions to EWRL.

Serve As Reviewer: ~Emmanuel_Esposito1

Track: Regular Track: unpublished work

Submission Number: 126