In the recent development ofwrious models of learning inspired by the PAC learning model (introduced by Valiant) there has been a trend towards models which are as representation independent as possible: We review this development and discuss the advantages of representation independence. Motivated by the research in learning, we propose a framework for studying the combinatorial properties of ...

We study a model of Probably Exactly Correct (PExact) learning that can be viewed either as the Exact model (learning from Equivalence Queries only) relaxed so that counterexamples to equivalence queries are distributionally drawn rather than adversarially chosen or as the Probably Approximately Correct (PAC) model strengthened to require a perfect hypothesis. We also introduce a model of Proba...

We give the first polynomial time prediction strategy for any PAC-learnable class C that probabilistically predicts the target with mistake probability poly(log(t)) t = Õ ( 1 t ) where t is the number of trials. The lower bound for the mistake probability is [HLW94]

We survey the fastest known algorithms for learning various expressive classes of Boolean functions in the Probably Approximately Correct (PAC) learning model.

We consider PAC learning of probability distributions (a.k.a. density estimation), where we are given an i.i.d. sample generated from an unknown target distribution, and want to output a distribution that is close to the target in total variation distance. Let F be an arbitrary class of probability distributions, and let F denote the class of k-mixtures of elements of F . Assuming the existence...

This paper applies the theory of Probably Approximately Correct (PAC) learning to multiple output feedforward threshold networks in which the weights conform to certain equivalences. It is shown that the sample size for reliable learning can be bounded above by a formula similar to that required for single output networks with no equivalences. The best previously obtained bounds are improved fo...

We report on the first complete calculation of the K_{L}-K_{S} mass difference, ΔM_{K}, using lattice QCD. The calculation is performed on a 2+1 flavor, domain wall fermion ensemble with a 330 MeV pion mass and a 575 MeV kaon mass. We use a quenched charm quark with a 949 MeV mass to implement Glashow-Iliopoulos-Maiani cancellation. For these heavier-than-physical particle masses, we obtain ΔM_...