Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
Without the proliferation of formal semantic annotations, the Semantic Web is certainly doomed to failure. In earlier work we presented a new paradigm to avoid this: the 'Sel...
This paper addresses the problem of applying powerful pattern recognition algorithms based on kernels to efficient visual tracking. Recently Avidan [1] has shown that object recog...
Oliver M. C. Williams, Andrew Blake, Roberto Cipol...
Abstract--Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replic...
In this paper we propose a scaling-up method that is applicable to essentially any induction algorithm based on discrete search. The result of applying the method to an algorithm ...