Statistics Papers
Document Type
Technical Report
Date of this Version
6-14-2007
Publication Source
EECS Department, University of California, Berkeley
Abstract
We study the rates of growth of the regret in online convex optimization. First, we show that a simple extension of the algorithm of Hazan et al eliminates the need for a priori knowledge of the lower bound on the second derivatives of the observed functions. We then provide an algorithm, Adaptive Online Gradient Descent, which interpolates between the results of Zinkevich for linear functions and of Hazan et al for strongly convex functions, achieving intermediate rates between √T and log T. Furthermore, we show strong optimality of the algorithm. Finally, we provide an extension of our results to general norms.
Recommended Citation
Bartlett, P., Hazan, E., & Rakhlin, A. (2007). Adaptive Online Gradient Descent. EECS Department, University of California, Berkeley, Retrieved from https://repository.upenn.edu/statistics_papers/163
Date Posted: 27 November 2017