34
7

Anytime Online-to-Batch Conversions, Optimism, and Acceleration

Abstract

A standard way to obtain convergence guarantees in stochastic convex optimization is to run an online learning algorithm and then output the average of its iterates: the actual iterates of the online learning algorithm do not come with individual guarantees. We close this gap by introducing a black-box modification to any online learning algorithm whose iterates converge to the optimum in stochastic scenarios. We then consider the case of smooth losses, and show that combining our approach with optimistic online learning algorithms immediately yields a fast convergence rate of O(L/T3/2+σ/T)O(L/T^{3/2}+\sigma/\sqrt{T}) on LL-smooth problems with σ2\sigma^2 variance in the gradients. Finally, we provide a reduction that converts any adaptive online algorithm into one that obtains the optimal accelerated rate of O~(L/T2+σ/T)\tilde O(L/T^2 + \sigma/\sqrt{T}), while still maintaining O~(1/T)\tilde O(1/\sqrt{T}) convergence in the non-smooth setting. Importantly, our algorithms adapt to LL and σ\sigma automatically: they do not need to know either to obtain these rates.

View on arXiv
Comments on this paper

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.