Online Learning and Online Convex Optimization

Lecture 1: Online Learning and Online Convex Optimization I 
Lecture 2: Online Learning and Online Convex Optimization II 
 

This series of talks is part of the Algorithms and Uncertainty Boot Camp. Videos for each talk area will be available through the links above.

Speaker: Nicolo Cesa-Bianchi, University of Milan

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.