Online Boosting with Bandit Feedback

Abstract

We consider the problem of online boosting for regression tasks, when only limited information is available to the learner. This setting is motivated by applications in reinforcement learning, in which only partial feedback is provided to the learner. We give an efficient regret minimization method that has two implications. First, we describe an online boosting algorithm with noisy multi-point bandit feedback. Next, we give a new projection-free online convex optimization algorithm with stochastic gradient access, that improves state-of-the-art guarantees in terms of efficiency. Our analysis offers a novel way of incorporating stochastic gradient estimators within Frank-Wolfe-type methods, which circumvents the instability encountered when directly applying projection-free optimization to the stochastic setting.