Improved Bounds for Testing Juntas

We consider the problem of testing functions for the property of being a k-junta (i.e., of depending on at most kvariables). Fischer, Kindler, Ron, Safra, and Samorodnitsky (J. Comput. Sys. Sci., 2004) showed that $\tilde{O}(k^2)/\epsilon$ queries are sufficient to test k-juntas, and conjectured that this bound is optimal for non-adaptive testing algorithms. Our main result is a non-adaptive algorithm for testing k-juntas with $\tilde{O}(k^{3/2})/\epsilon$ queries. This algorithm disproves the conjecture of Fischer et al. We also show that the query complexity of non-adaptive algorithms for testing juntas has a lower bound of $\min \big(\tilde{\Omega}(k/\epsilon), 2^k/k\big)$, essentially improving on the previous best lower bound of i¾?(k).

[1]  L. H. Harper Optimal Assignments of Numbers to Vertices , 1964 .

[2]  A. J. Bernstein,et al.  Maximally Connected Arrays on the n-Cube , 1967 .

[3]  Mihir Bellare,et al.  Free Bits, PCPs, and Nonapproximability-Towards Tight Results , 1998, SIAM J. Comput..

[4]  Avrim Blum,et al.  Relevant Examples and Relevant Features: Thoughts from Computational Learning Theory , 1994 .

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

[6]  Sergiu Hart,et al.  A note on the edges of the n-cube , 1976, Discret. Math..

[7]  Hana Chockler,et al.  A lower bound for testing juntas , 2004, Inf. Process. Lett..

[8]  Nisheeth K. Vishnoi,et al.  On the Fourier spectrum of symmetric Boolean functions with applications to learning symmetric juntas , 2005, 20th Annual IEEE Conference on Computational Complexity (CCC'05).

[9]  Tatsuie Tsukiji,et al.  Finding Relevant Variables in PAC Model with Membership Queries , 1999, ALT.

[10]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[11]  Rocco A. Servedio,et al.  Testing for Concise Representations , 2007, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

[12]  Dana Ron,et al.  Testing Basic Boolean Formulae , 2002, SIAM J. Discret. Math..

[13]  Mihir Bellare,et al.  Free bits, PCPs and non-approximability-towards tight results , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[14]  Dana Ron,et al.  On the Benefits of Adaptivity in Property Testing of Dense Graphs , 2010, Algorithmica.

[15]  Ryan O'Donnell,et al.  Learning functions of k relevant variables , 2004, J. Comput. Syst. Sci..

[16]  Andrew Chi-Chih Yao,et al.  Probabilistic computations: Toward a unified measure of complexity , 1977, 18th Annual Symposium on Foundations of Computer Science (sfcs 1977).

[17]  Avrim Blum Learning a Function of r Relevant Variables , 2003, COLT.

[18]  Guy Kindler,et al.  Testing juntas , 2002, J. Comput. Syst. Sci..

[19]  O. Svensson,et al.  Inapproximability Results for Sparsest Cut, Optimal Linear Arrangement, and Precedence Constrained Scheduling , 2007, FOCS 2007.

[20]  Ronitt Rubinfeld,et al.  Robust Characterizations of Polynomials with Applications to Program Testing , 1996, SIAM J. Comput..

[21]  Rocco A. Servedio,et al.  Quantum Algorithms for Learning and Testing Juntas , 2007, Quantum Inf. Process..