We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...
We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model. This model generalizes previously considered models of learning with noise. Th...
We present the first PAC bounds for learning parameters of Conditional Random Fields [12] with general structures over discrete and real-valued variables. Our bounds apply to com...
We consider the general, widely applicable problem of selecting from n real-valued random variables a subset of size m of those with the highest means, based on as few samples as ...
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...