On the asymptotic optimality of the comb strategy for prediction with expert advice by Prof. Erhan Bayraktar (Susan M. Smith Professor of Mathematics, U of Michigan)

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 using techniques from stochastic analysis and PDEs. Then, we use this expansion to prove that as conjectured in Gravin, Peres and Sivan the comb strategies are indeed asymptotically optimal for the adversary in the case of 4 experts.