Abstract

In this tutorial we introduce the framework of online convex optimization, the standard model for the design and analysis of online learning algorithms. After defining the notions of regret and regularization, we describe and analyze some of the most important online algorithms, including Mirror Descent, AdaGrad, and Online Newton Step.

The second session of this mini course will take place on Wednesday, August 24th, 2016 2:00 pm – 2:45 pm.

Attachment

Video Recording