Translator Disclaimer
December 2020 On the asymptotic optimality of the comb strategy for prediction with expert advice
Erhan Bayraktar, Ibrahim Ekren, Yili Zhang
Ann. Appl. Probab. 30(6): 2517-2546 (December 2020). DOI: 10.1214/20-AAP1565

Abstract

For the problem of prediction with expert advice in the adversarial setting with geometric stopping, we compute the exact leading order expansion for the long time behavior of the value function. Then, we use this expansion to prove that as conjectured in Gravin, Peres and Sivan (In Proceedings of the Twenty-Seventh Annual ACM-SIAM Symposium on Discrete Algorithms (2016) 528–547, ACM), the comb strategies are indeed asymptotically optimal for the adversary in the case of $4$ experts.

Citation

Download Citation

Erhan Bayraktar. Ibrahim Ekren. Yili Zhang. "On the asymptotic optimality of the comb strategy for prediction with expert advice." Ann. Appl. Probab. 30 (6) 2517 - 2546, December 2020. https://doi.org/10.1214/20-AAP1565

Information

Received: 1 February 2019; Revised: 1 December 2019; Published: December 2020
First available in Project Euclid: 14 December 2020

Digital Object Identifier: 10.1214/20-AAP1565

Subjects:
Primary: 35J60, 35L02, 68T05

Rights: Copyright © 2020 Institute of Mathematical Statistics

JOURNAL ARTICLE
30 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

SHARE
Vol.30 • No. 6 • December 2020
Back to Top