Toward Attribute Efficient Learning Algorithms
Abstract
We make progress on two important problems regarding attribute efficient learnability. First, we give an algorithm for learning decision lists of length over variables using examples and time . This is the first algorithm for learning decision lists that has both subexponential sample complexity and subexponential running time in the relevant parameters. Our approach establishes a relationship between attribute efficient learning and polynomial threshold functions and is based on a new construction of low degree, low weight polynomial threshold functions for decision lists. For a wide range of parameters our construction matches a 1994 lower bound due to Beigel for the ODDMAXBIT predicate and gives an essentially optimal tradeoff between polynomial threshold function degree and weight. Second, we give an algorithm for learning an unknown parity function on out of variables using examples in time polynomial in . For this yields a polynomial time algorithm with sample complexity . This is the first polynomial time algorithm for learning parity on a superconstant number of variables with sublinear sample complexity.
Cite
@article{arxiv.cs/0311042,
title = {Toward Attribute Efficient Learning Algorithms},
author = {Adam R. Klivans and Rocco A. Servedio},
journal= {arXiv preprint arXiv:cs/0311042},
year = {2007}
}