Adaptive Online Gradient Descent

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.

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Peter L. Bartlett, Elad Hazan, Alexander Rakhlin
• Keywords: Hazan Et Al, Information Technology, NIPS 2007, Online Convex Optimization, Online Gradient Descent