We prove general exponential moment inequalities for averages of [0,1]valued iid random variables and use them to tighten the PAC Bayesian Theorem. The logarithmic dependence on t...
For hyper-rectangles in Rd Auer et al. [1] proved a PAC bound of O 1 (d + log 1 ) , where and are the accuracy and confidence parameters. It is still an open question whether one...
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 present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
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...