Abstract
Let X ⊆ R n and let \({\cal C}\) be a class of functions mapping ℝn → { − 1,1}. The famous VC-Theorem states that a random subset S of X of size \(O(\frac{d}{\epsilon^{2}} \log \frac{d}{\epsilon})\), where d is the VC-Dimension of \({\cal C}\), is (with constant probability) an ε-approximation for \({\cal C}\) with respect to the uniform distribution on X. In this work, we revisit the problem of constructing S explicitly. We show that for any X ⊆ ℝn and any Boolean function class \({\cal C}\) that is uniformly approximated by degree k polynomials, an ε-approximation S can be be constructed deterministically in time poly(n k,1/ε,|X|) provided that \(\epsilon =\Omega\left(W \cdot \sqrt{\frac{\log{|X|}}{|X|}}\right)\) where W is the weight of the approximating polynomial. Previous work due to Chazelle and Matousek suffers an d O(d) factor in the running time and results in superpolynomial-time algorithms, even in the case where k = O(1).
We also give the first hardness result for this problem and show that the existence of a poly(n k,|X|,1/ε)-time algorithm for deterministically constructing ε-approximations for circuits of size n k for every k would imply that P = BPP. This indicates that in order to construct explicit ε-approximations for a function class \({\cal C}\), we should not focus solely on \({\cal C}\)’s VC-dimension.
Our techniques use deterministic algorithms for discrepancy minimization to construct hard functions for Boolean function classes over arbitrary domains (in contrast to the usual results in pseudorandomness where the target distribution is uniform over the hypercube).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chattopadhyay, E., Klivans, A., Kothari, P.: An explicit vc-theorem for low degree polynomials. Full Version (2012)
Chazelle, B.: The discrepancy method: randomness and complexity. Cambridge University Press, New York (2000)
Chazelle, B., Matousek, J.: On linear-time deterministic algorithms for optimization problems in fixed dimension. J. Algorithms 21(3), 579–597 (1996)
Feldman, D., Langberg, M.: A unified framework for approximating and clustering data. In: STOC, pp. 569–578 (2011)
Impagliazzo, R., Wigderson, A.: P = BPP unless E has sub-exponential circuits: Derandomizing the XOR lemma (preliminary version). In: Proceedings of the 29th STOC, pp. 220–229. ACM Press (1996)
Li, Y., Long, P.M., Srinivasan, A.: Improved bounds on the sample complexity of learning. Journal of Computer and System Sciences 62, 2001 (2000)
Matousek, J.: Geometric Discrepancy: An Illustrated Guide (Algorithms and Combinatorics), 1st edn. Springer (1999)
Nisan, N.: Pseudorandom generators for space-bounded computation. Combinatorica 12(4), 449–461 (1992)
Nisan, N.: RL ⊆ SC. In: STOC, pp. 619–623 (1992)
O’Donnell, R., Servedio, R.A.: New degree bounds for polynomial threshold functions. In: STOC, pp. 325–334 (2003)
Pach, J., Agrawal, P.: Combinatorial Geometry. Wiley-Interscience (October 1995)
Sivakumar, D.: Algorithmic derandomization via complexity theory. In: IEEE Conference on Computational Complexity, p. 10 (2002)
Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications 16(2), 264–280 (1971)
Vapnik, V.N.: Statistical learning theory. Wiley (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chattopadhyay, E., Klivans, A., Kothari, P. (2012). An Explicit VC-Theorem for Low-Degree Polynomials. In: Gupta, A., Jansen, K., Rolim, J., Servedio, R. (eds) Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques. APPROX RANDOM 2012 2012. Lecture Notes in Computer Science, vol 7408. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32512-0_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-32512-0_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32511-3
Online ISBN: 978-3-642-32512-0
eBook Packages: Computer ScienceComputer Science (R0)