Experimental Evidence for Asymptotic Non-Optimality of Comb Adversary Strategy

Abstract

For the problem of prediction with expert advice in the adversarial setting with finite stopping time, we give strong computer evidence that the comb strategy for $k=5$ experts is not asymptotically optimal, thereby giving strong evidence against a conjecture of Gravin, Peres, and Sivan.

arXiv comment3 pages, 1 figure

References in corpus (1)

• On the asymptotic optimality of the comb strategy for prediction with expert advice