We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An eectiveperformance measure is the minimax re...
We investigate the computational complexity of the task of detecting dense regions of an unknown distribution from un-labeled samples of this distribution. We introduce a formal l...
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...
Alexander L. Strehl, Chris Mesterharm, Michael L. ...