Learning Read-Constant Polynomials of Constant Degree Modulo Composites

Boolean functions that have constant degree polynomial representation over a fixed finite ring form a natural and strict subclass of the complexity class ACC0. They are also precisely the functions computable efficiently by programs over fixed and finite nilpotent groups. This class is not known to be learnable in any reasonable learning model.In this paper, we provide a deterministic polynomial time algorithm for learning Boolean functions represented by polynomials of constant degree over arbitrary finite rings from membership queries, with the additional constraint that each variable in the target polynomial appears in a constant number of monomials. Our algorithm extends to superconstant but low degree polynomials and still runs in quasipolynomial time.

[1]  Ran Raz,et al.  Pseudorandom Generators for Regular Branching Programs , 2014, SIAM J. Comput..

[2]  Nader H. Bshouty,et al.  Learning Matrix Functions over Rings , 1997, EuroCOLT.

[3]  Roman Smolensky,et al.  Algebraic methods in the theory of lower bounds for Boolean circuit complexity , 1987, STOC.

[4]  Parikshit Gopalan.  Constructing Ramsey graphs from Boolean function representations , 2006, 21st Annual IEEE Conference on Computational Complexity (CCC'06).

[5]  Pavel Pudlák,et al.  Pseudorandom generators for group products: extended abstract , 2011, STOC '11.

[6]  Arkadev Chattopadhyay.  Multilinear Polynomials Modulo Composites , 2010, Bull. EATCS.

[7]  Joshua Brody,et al.  The Coin Problem and Pseudorandomness for Branching Programs , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

[8]  David A. Mix Barrington,et al.  Bounded-width polynomial-size branching programs recognize exactly those languages in NC1 , 1986, STOC '86.

[9]  Howard Straubing,et al.  Superlinear Lower Bounds for Bounded-Width Branching Programs , 1995, J. Comput. Syst. Sci..

[10]  Lisa Hellerstein,et al.  Complexity theoretic hardness results for query learning , 1998, computational complexity.

[11]  J. C. Jackson.  Learning Functions Represented as Multiplicity Automata , 1997 .

[12]  Denis Thérien,et al.  Non-Uniform Automata Over Groups , 1987, Inf. Comput..

[13]  David A. Mix Barrington,et al.  Representing Boolean functions as polynomials modulo composite numbers , 1992, STOC '92.

[14]  Howard Straubing,et al.  Non-Uniform Automata Over Groups , 1990, Inf. Comput..

[15]  Klim Efremenko,et al.  3-Query Locally Decodable Codes of Subexponential Length , 2008 .

[16]  Howard Straubing,et al.  Superlinear lower bounds for bounded-width branching programs , 1991, [1991] Proceedings of the Sixth Annual Structure in Complexity Theory Conference.

[17]  Linda Sellie,et al.  Learning sparse multivariate polynomials over a field with queries and counterexamples , 1993, COLT '93.

[18]  Eyal Kushilevitz,et al.  On Learning Read-k-Satisfy-j DNF , 1998, SIAM J. Comput..

[19]  J. Bourgain.  Estimation of certain exponential sums arising in complexity theory , 2005 .

[20]  Vince Grolmusz.  On the Weak mod m Representation of Boolean Functions , 1995, Chic. J. Theor. Comput. Sci..

[21]  Manfred K. Warmuth,et al.  Learning nested differences of intersection-closed concept classes , 2004, Machine Learning.

[22]  Denis Thérien,et al.  On the Languages Recognized by Nilpotent Groups (a translation of "Sur les Langages Reconnus par des Groupes Nilpotents") , 2001, Electron. Colloquium Comput. Complex..

[23]  Marek Karpinski,et al.  Learning read-once formulas with queries , 1993, JACM.

[24]  Denis Thérien,et al.  Finite monoids and the fine structure of NC1 , 1987, STOC.

[25]  Gábor Tardos,et al.  A lower bound on the mod 6 degree of the OR function , 1998, computational complexity.

[26]  A. Razborov.  Lower bounds on the size of bounded depth circuits over a complete basis with logical addition , 1987 .

[27]  Denis Thérien,et al.  An Algebraic Perspective on Boolean Function Learning , 2009, ALT.

[28]  Pavel Pudlák,et al.  Pseudorandom Generators for Group Products , 2010, Electron. Colloquium Comput. Complex..

[29]  Vijay Raghavan,et al.  Read-Twice DNF Formulas are Properly Learnable , 1994, Inf. Comput..