PExact = Exact Learning

The Probably Exact model (PExact) is a relaxation of the Exact model, introduced in by Bshouty. In this paper, we show that the PExact model is equivalent to the Exact model.

[1]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[2]  Avrim Blum,et al.  Separating distribution-free and mistake-bound learning models over the Boolean domain , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[3]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[4]  D. Angluin,et al.  Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle , 1991, Machine Learning.

[5]  Nader H. Bshouty,et al.  Exploring learnability between exact and PAC , 2005, J. Comput. Syst. Sci..

[6]  Shai Ben-David,et al.  Online Learning versus Offline Learning , 1995, Machine Learning.

[7]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[8]  N. Bshouty.  A Booster for the PAExact model , 2003 .

[9]  Yishay Mansour,et al.  Boosting Using Branching Programs , 2000, J. Comput. Syst. Sci..

[10]  Nader H. Bshouty.  Exact Learning of Formulas in Parallel , 2004, Machine Learning.

[11]  Dmitry Gavinsky,et al.  PAC=PAExact and other equivalent models in learning , 2002, The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings..