Skip to yearly menu bar Skip to main content


Optimistic Bandit Convex Optimization

Scott Yang · Mehryar Mohri

Area 5+6+7+8 #93

Keywords: [ Convex Optimization ] [ Online Learning ] [ Learning Theory ] [ Bandit Algorithms ]

Abstract: We introduce the general and powerful scheme of predicting information re-use in optimization algorithms. This allows us to devise a computationally efficient algorithm for bandit convex optimization with new state-of-the-art guarantees for both Lipschitz loss functions and loss functions with Lipschitz gradients. This is the first algorithm admitting both a polynomial time complexity and a regret that is polynomial in the dimension of the action space that improves upon the original regret bound for Lipschitz loss functions, achieving a regret of $\widetilde O(T^{11/16}d^{3/8})$. Our algorithm further improves upon the best existing polynomial-in-dimension bound (both computationally and in terms of regret) for loss functions with Lipschitz gradients, achieving a regret of $\widetilde O(T^{8/13} d^{5/3})$.

Live content is unavailable. Log in and register to view live content