Abstract: In recent years online learning (sequential prediction) has received much attention as it often produces fast and simple learning algorithms that enjoy robustness to changing or even adversarial data sources. However, despite the extensive existing literature on online learning, our theoretical understanding of the framework has been rather lacking. Most existing analyses have been case by case, and there is a lack of a general theory and methodology for designing online learning algorithms for the problem at hand. The goal of this talk is to first present a new general theory for online learning that parallels results from statistical learning theory. Next, building on this general theory, I will provide a generic recipe for deriving online learning algorithms. Finally, we shall see how the tools and techniques presented can be used for designing efficient learning algorithms for several interesting problems including online collaborative filtering, node classification in social networks etc.
Bio: Karthik Sridharan is currently a Postdoctoral research scholar at the University of Pennsylvania. He obtained his PhD from the Toyota Technological Institute at Chicago. He works in the areas of machine learning, optimization and statistics. The main focus of his work has been in mathematical analysis and design of learning algorithms for online and statistical learning problems and in exploring connections between optimization and learning.