On the complexity of approximating the VC dimension

We study the complexity of approximating the VC dimension of a collection of sets, when the sets are encoded succinctly by a small circuit. We show that this problem is: /spl Sigma//sub 3//sup p/-hard to approximate to within a factor 2-/spl epsiv/ for any /spl epsiv/>0; approximable in A/spl Mscr/ to within a factor 2; and A/spl Mscr/-hard to approximate to within a factor N/sup /spl epsiv// for some constant /spl epsiv/>0. To obtain the /spl Sigma//sub 3//sup 9/-hardness results we solve a randomness extraction problem using list-decodable binary codes; for the positive results we utilize the Sauer-Shelah(-Perles) Lemma. The exact value of /spl epsiv/ in the A/spl Mscr/-hardness result depends on the degree achievable by explicit disperser constructions.

[1]  Marcus Schäfer.  Deciding the Vapnik-Cervonenkis dimension is ...-complete , 1995 .

[2]  László Babai,et al.  Arthur-Merlin Games: A Randomized Proof System, and a Hierarchy of Complexity Classes , 1988, J. Comput. Syst. Sci..

[3]  Nathan Linial,et al.  Results on learnability and the Vapnik-Chervonenkis dimension , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[4]  Venkatesan Guruswami,et al.  List decoding algorithms for certain concatenated codes , 2000, STOC '00.

[5]  K. Ko,et al.  On the Complexity of Min-Max Optimization Problems and their Approximation , 1995 .

[6]  Michael Sipser,et al.  Expanders, Randomness, or Time versus Space , 1988, Journal of computer and system sciences (Print).

[7]  S. Shelah.  A combinatorial problem; stability and order for models and theories in infinitary languages. , 1972 .

[8]  Mihalis Yannakakis,et al.  On limited nondeterminism and the complexity of the V-C dimension , 1993, [1993] Proceedings of the Eigth Annual Structure in Complexity Theory Conference.

[9]  Norbert Sauer,et al.  On the Density of Families of Sets , 1972, J. Comb. Theory A.

[10]  Noam Nisan,et al.  Extracting Randomness: A Survey and New Constructions , 1999, J. Comput. Syst. Sci..

[11]  Amnon Ta-Shma,et al.  Loss-less condensers, unbalanced expanders, and extractors , 2001, STOC '01.

[12]  Oded Goldreich,et al.  The bit extraction problem or t-resilient functions , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[13]  C. Umans.  Hardness of Approximating p 2 Minimization Problems , 1999 .

[14]  Amnon Ta-Shma,et al.  Extractors from Reed-Muller Codes , 2001, Electron. Colloquium Comput. Complex..

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

[16]  Nathan Linial,et al.  Results on learnability and the Vapnick-Chervonenkis dimension , 1988, COLT '88.

[17]  Venkatesan Guruswami,et al.  Expander-based constructions of efficiently decodable codes , 2001, Proceedings 2001 IEEE International Conference on Cluster Computing.

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

[19]  Mark G. Karpovsky,et al.  Coordinate density of sets of vectors , 1978, Discret. Math..

[20]  Umesh V. Vazirani,et al.  Strong communication complexity or generating quasi-random sequences from two communicating semi-random sources , 1987, Comb..

[21]  Noga Alon,et al.  On the density of sets of vectors , 1983, Discret. Math..

[22]  Luca Trevisan,et al.  Construction of extractors using pseudo-random generators (extended abstract) , 1999, STOC '99.