Quantum Algorithm for Online Convex Optimization
This work demonstrates potential quantum advantages for online convex optimization, a foundational problem in machine learning and optimization, though it is incremental in extending quantum methods to this domain.
The paper tackles the problem of zeroth-order online convex optimization by presenting quantum algorithms that achieve O(√T) regret without dimension dependence, outperforming classical optimal O(√nT) regret, and O(log T) regret for strongly convex functions, matching classical full-information bounds.
We explore whether quantum advantages can be found for the zeroth-order online convex optimization problem, which is also known as bandit convex optimization with multi-point feedback. In this setting, given access to zeroth-order oracles (that is, the loss function is accessed as a black box that returns the function value for any queried input), a player attempts to minimize a sequence of adversarially generated convex loss functions. This procedure can be described as a $T$ round iterative game between the player and the adversary. In this paper, we present quantum algorithms for the problem and show for the first time that potential quantum advantages are possible for problems of online convex optimization. Specifically, our contributions are as follows. (i) When the player is allowed to query zeroth-order oracles $O(1)$ times in each round as feedback, we give a quantum algorithm that achieves $O(\sqrt{T})$ regret without additional dependence of the dimension $n$, which outperforms the already known optimal classical algorithm only achieving $O(\sqrt{nT})$ regret. Note that the regret of our quantum algorithm has achieved the lower bound of classical first-order methods. (ii) We show that for strongly convex loss functions, the quantum algorithm can achieve $O(\log T)$ regret with $O(1)$ queries as well, which means that the quantum algorithm can achieve the same regret bound as the classical algorithms in the full information setting.