Logarithmic Regret for Online Gradient Descent Beyond Strong Convexity
[edit]
Proceedings of Machine Learning Research, PMLR 89:295303, 2019.
Abstract
Hoffman’s classical result gives a bound on the distance of a point from a convex and compact polytope in terms of the magnitude of violation of the constraints. Recently, several results showed that Hoffman’s bound can be used to derive stronglyconvexlike rates for firstorder methods for \textit{offline} convex optimization of curved, though not strongly convex, functions, over polyhedral sets. In this work, we use this classical result for the first time to obtain faster rates for \textit{online convex optimization} over polyhedral sets with curved convex, though not strongly convex, loss functions. We show that under several reasonable assumptions on the data, the standard \textit{Online Gradient Descent} algorithm guarantees logarithmic regret. To the best of our knowledge, the only previous algorithm to achieve logarithmic regret in the considered settings is the \textit{Online Newton Step} algorithm which requires quadratic (in the dimension) memory and at least quadratic runtime per iteration, which greatly limits its applicability to largescale problems. In particular, our results hold for \textit{semiadversarial} settings in which the data is a combination of an arbitrary (adversarial) sequence and a stochastic sequence, which might provide reasonable approximation for many realworld sequences, or under a natural assumption that the data is lowrank. We demonstrate via experiments that the regret of OGD is indeed comparable to that of ONS (and even far better) on curved though not stronglyconvex losses.
Related Material


