We develop a theory of online learning by defining several complexity measures. Among them are analogues of Rademacher complexity, covering numbers and fatshattering dimension fro...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
Abstract. Nonlinear component analysis is a popular nonlinear feature extraction method. It generally uses eigen-decomposition technique to extract the principal components. But th...
A significant input-data uncertainty is often present in practical situations. One approach to coping with this uncertainty is to describe the uncertainty with scenarios. A scenar...
Jurij Mihelic, Amine Mahjoub, Christophe Rapine, B...
This paper reviews the connections between Graphplan's planning-graph and the dynamic constraint satisfaction problem and motivates the need for adapting CSP search technique...
In this paper we prove lower bounds on randomized multiparty communication complexity, both in the blackboard model (where each message is written on a blackboard for all players ...