An O(n^(log log n)) Learning Algorithm for DNT under the Uniform Distribution

We show that a DNF with terms of size at most d can be approximated by a function with at most d O(d log1=") non zero Fourier coeecients such that the expected error squared, with respect to the uniform distribution, is at most ". This property is used to derive a learning algorithm for DNF, under the uniform distribution. The learning algorithm uses queries and learns, with respect to the uniform distribution, a DNF with terms of size at most d in time polynomial in n and d O(dlog 1="). The interesting implications are for the case when " is constant. In this case our algorithm learns a DNF with a polynomial number of terms in time n O(loglog n) , and a DNF with terms of size at most O(log n= log log n) in polynomial time.

[1]  Michael Sipser,et al.  Parity, circuits, and the polynomial-time hierarchy , 1981, 22nd Annual Symposium on Foundations of Computer Science (sfcs 1981).

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

[3]  A. Yao Separating the polynomial-time hierarchy by oracles , 1985 .

[4]  J. Håstad Computational limitations of small-depth circuits , 1987 .

[5]  Leslie G. Valiant,et al.  On the learnability of Boolean formulae , 1987, STOC.

[6]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[7]  Noam Nisan,et al.  Constant depth circuits, Fourier transform, and learnability , 1989, 30th Annual Symposium on Foundations of Computer Science.

[8]  Leonid A. Levin,et al.  A hard-core predicate for all one-way functions , 1989, STOC '89.

[9]  Karsten A. Verbeurgt Learning DNF under the uniform distribution in quasi-polynomial time , 1990, COLT '90.

[10]  Jehoshua Bruck,et al.  Harmonic Analysis of Polynomial Threshold Functions , 1990, SIAM J. Discret. Math..

[11]  H. Aizenstein,et al.  Exact learning of read-twice DNF formulas , 1991, [1991] Proceedings 32nd Annual Symposium of Foundations of Computer Science.

[12]  Dana Angluin,et al.  When won't membership queries help? , 1991, STOC '91.

[13]  Yishay Mansour,et al.  Learning monotone ku DNF formulas on product distributions , 1991, COLT '91.

[14]  William Aiello,et al.  Learning the Fourier spectrum of probabilistic lists and trees , 1991, SODA '91.

[15]  Jehoshua Bruck,et al.  On the Power of Threshold Circuits with Small Weights , 1991, SIAM J. Discret. Math..

[16]  Eyal Kushilevitz,et al.  Learning decision trees using the Fourier spectrum , 1991, STOC '91.

[17]  Jehoshua Bruck,et al.  Polynomial threshold functions, AC functions and spectrum norms , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.