On the Fourier spectrum of monotone functions

In this paper, monotone Boolean functions are studied using harmonic analysis on the cube. The main result is that any monotone Boolean function has most of its power spectrum on its Fourier coefficients of “degree” at most O(=n) under any product distribution. This is similar to a result of Linial et al. [1993], which showed that AC functions have almost all of their power spectrum on the coefficients of degree, at most (log n), under the uniform distribution. As a consequence of the main result, the following two corollaries are obtained: —For any e . 0, monotone Boolean functions are PAC learnable with error e under product distributions in time 2O((1/e)n). —Any monotone Boolean function can be approximated within error e under product distributions by a non-monotone Boolean circuit of size 2O(1/en) and depth O(1/e =n). The learning algorithm runs in time subexponential as long as the required error is V(1/(=n log n)). It is shown that this is tight in the sense that for any subexponential time algorithm there is a monotone Boolean function for which this algorithm cannot approximate with error better than O(1/=n). The main result is also applied to other problems in learning and complexity theory. In learning theory, several polynomial-time algorithms for learning some classes of monotone Boolean functions, such as Boolean functions with O(logn/log log n) relevant variables, are presented. In complexity theory, some questions regarding monotone NP-complete problems are addressed.

[1]  Ingo Wegener,et al.  The complexity of Boolean functions , 1987 .

[2]  Akira Maruoka,et al.  Learning monotone log-term DNF formulas , 1994, COLT '94.

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

[4]  Michael Kearns,et al.  Efficient noise-tolerant learning from statistical queries , 1993, STOC.

[5]  Torben Hagerup,et al.  A Guided Tour of Chernoff Bounds , 1990, Inf. Process. Lett..

[6]  Eyal Kushilevitz,et al.  Learning Decision Trees Using the Fourier Spectrum , 1993, SIAM J. Comput..

[7]  Yishay Mansour,et al.  Weakly learning DNF and characterizing statistical query learning using Fourier analysis , 1994, STOC '94.

[8]  Yishay Mansour,et al.  Randomized Interpolation and Approximation of Sparse Polynomials , 1992, SIAM J. Comput..

[9]  Béla Bollobás,et al.  Random Graphs , 1985 .

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

[11]  Leslie G. Valiant,et al.  Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.

[12]  Michael Kearns,et al.  Computational complexity of machine learning , 1990, ACM distinguished dissertations.

[13]  Jeffrey C. Jackson,et al.  An efficient membership-query algorithm for learning DNF with respect to the uniform distribution , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[14]  Nathan Linial,et al.  The influence of variables on Boolean functions , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[15]  Sean W. Smith,et al.  Improved learning of AC0 functions , 1991, COLT '91.

[16]  Yishay Mansour,et al.  An O(nlog log n) learning algorithm for DNF under the uniform distribution , 1992, COLT '92.

[17]  J. Spencer.  Ten lectures on the probabilistic method , 1987 .

[18]  Leslie G. Valiant,et al.  A general lower bound on the number of examples needed for learning , 1988, COLT '88.

[19]  Nader H. Bshouty.  Simple learning algorithms using divide and conquer , 1995, COLT '95.

[20]  Yishay Mansour,et al.  Learning Boolean Functions via the Fourier Transform , 1994 .

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

[22]  Noam Nisan,et al.  Constant depth circuits, Fourier transform, and learnability , 1993, JACM.

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

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

[25]  Hugo Krawczyk,et al.  The Shrinking Generator , 1994, CRYPTO.

[26]  Noga Alon,et al.  The Probabilistic Method , 2015, Fundamentals of Ramsey Theory.

[27]  Mihir Bellare.  A technique for upper bounding the spectral norm with applications to learning , 1992, COLT '92.