We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Abstract. We propose an online learning algorithm to tackle the problem of learning under limited computational resources in a teacher-student scenario, over multiple visual cues. ...
To learn concepts over massive data streams, it is essential to design inference and learning methods that operate in real time with limited memory. Online learning methods such a...
This case study compares students' learning experience and outcomes in the lecture and online versions of a first-year introductory computing course offered at the Department...
We consider the problem of revenue maximization in online auctions, that is, auctions in which bids are received and dealt with one-by-one. In this note, we demonstrate that resul...