In this paper we study a paradigm to generalize online classification algorithms for binary classification problems to multiclass problems. The particular hypotheses we investig...
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
Abstract. Littlestone developed a simple deterministic on-line learning algorithm for learning k-literal disjunctions. This algorithm (called Winnow) keeps one weight for each of t...
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...
We describe and analyze an algorithmic framework for online classification where each online trial consists of multiple prediction tasks that are tied together. We tackle the prob...