20
18

Online Strongly Convex Optimization with Unknown Delays

Abstract

We investigate the problem of online convex optimization with unknown delays, in which the feedback of a decision arrives with an arbitrary delay. Previous studies have presented a delayed variant of online gradient descent (OGD), and achieved the regret bound of O(T+D)O(\sqrt{T+D}) by only utilizing the convexity condition, where DD is the sum of delays over TT rounds. In this paper, we further exploit the strong convexity to improve the regret bound. Specifically, we first extend the delayed variant of OGD for strongly convex functions, and establish a better regret bound of O(dlogT)O(d\log T), where dd is the maximum delay. The essential idea is to let the learning rate decay with the total number of received feedback linearly. Furthermore, we consider the more challenging bandit setting, and obtain similar theoretical guarantees by incorporating the classical multi-point gradient estimator into our extended method. To the best of our knowledge, this is the first work that solves online strongly convex optimization under the general delayed setting.

View on arXiv
Comments on this paper