The time until the final zero crossing of random sums with application to nonparametric bandit theory (Q1335239)

Motivated by problems in machine learning and more fundamentally by non- Bayesian nonparametric problems in sequential design of experiments, the present work deals with the task of attaining probability bounds for the number of times suboptimal bandits are chosen in a nonterminating sequence of experiments. To the author's knowledge, previously only the growth of the expectation of incorrect choices has been examined. The derivation is founded, in part, on new contributions to the theory of zero crossings for sums of biased, independent, identically distributed random variables.