Abstract
We use the connection between resource-bounded dimension and the online mistake-bound model of learning to show that the following classes have polynomial-time dimension zero.
-
1.
The class of problems which reduce to nondense sets via a majority reduction.
-
2.
The class of problems which reduce to nondense sets via an iterated reduction that composes a bounded-query truth-table reduction with a conjunctive reduction.
Intuitively, polynomial-time dimension is a means of quantifying the size and complexity of classes within the exponential time complexity class E. The class P has dimension 0, E itself has dimension 1, and any class with dimension less than 1 cannot contain E. As a corollary, it follows that all sets which are hard for E under these types of reductions are exponentially dense. The first item subsumes two previous results and the second item answers a question of Lutz and Mayordomo. Our proofs use Littlestone’s Winnow2 algorithm for learning r-of-k threshold functions and Maass and Turán’s algorithm for learning halfspaces.
Similar content being viewed by others
References
Agrawal, M., Arvind, V.: Geometric sets of low information content. Theor. Comput. Sci. 158(12), 193–219 (1996)
Arvind, V., Han, Y., Hemachandra, L., Köbler, J., Lozano, A., Mundhenk, M., Ogiwara, M., Schöning, U., Silvestri, R., Thierauf, T.: Reductions to sets of low information content. In: Ambos-Spies, K., Homer, S., Schöning, U. (eds.) Complexity Theory: Current Research, pp. 1–45. Cambridge University Press, Cambridge (1993)
Athreya, K.B., Hitchcock, J.M., Lutz, J.H., Mayordomo, E.: Effective strong dimension in algorithmic information and computational complexity. SIAM J. Comput. 37(3), 671–705 (2007)
Fu, B.: With quasilinear queries EXP is not polynomial time Turing reducible to sparse sets. SIAM J. Comput. 24(5), 1082–1090 (1995)
Fu, B.: Personal communication (2006)
Hitchcock, J.M.: Online learning and resource-bounded dimension: winnow yields new lower bounds for hard sets. SIAM J. Comput. 36(6), 1696–1708 (2007)
Hitchcock, J.M., Lutz, J.H., Mayordomo, E.: The fractal geometry of complexity classes. SIGACT News 36(3), 24–38 (2005)
Lindner, W., Schuler, R., Watanabe, O.: Resource-bounded measure and learnability. Theory Comput. Syst. 33(2), 151–170 (2000)
Littlestone, N.: Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm. Mach. Learn. 2(4), 285–318 (1987)
Lutz, J.H.: Almost everywhere high nonuniform complexity. J. Comput. Syst. Sci. 44(2), 220–258 (1992)
Lutz, J.H.: The quantitative structure of exponential time. In: Hemaspaandra, L.A., Selman, A.L. (eds.) Complexity Theory Retrospective II, pp. 225–254. Springer, Berlin (1997)
Lutz, J.H.: Dimension in complexity classes. SIAM J. Comput. 32(5), 1236–1259 (2003)
Lutz, J.H., Mayordomo, E.: Measure, stochasticity, and the density of hard languages. SIAM J. Comput. 23(4), 762–779 (1994)
Lutz, J.H., Mayordomo, E.: Twelve problems in resource-bounded measure. Bull. Eur. Assoc. Theor. Comput. Sci. 68, 64–80 (1999). Also in Current Trends in Theoretical Computer Science: Entering the 21st Century, pp. 83–101. World Scientific, Singapore (2001)
Lutz, J.H., Zhao, Y.: The density of weakly complete problems under adaptive reductions. SIAM J. Comput. 30(4), 1197–1210 (2000)
Maass, W., Turán, G.: How fast can a threshold gate learn? In: Hanson, S.J., Drastal, G.A., Rivest, R.L. (eds.) Computational Learning Theory and Natural Learning Systems, vol. I: Constraints and Prospects, pp. 381–414. MIT Press, Cambridge (1994)
Vaidya, P.M.: A new algorithm for minimizing convex functions over convex sets. In: Proceedings of the 30th IEEE Symposium on Foundations of Computer Science, pp. 338–349. IEEE Computer Society, Los Alamitos (1989)
Watanabe, O.: Polynomial time reducibility to a set of small density. In: Proceedings of the Second Structure in Complexity Theory Conference, pp. 138–146. IEEE Computer Society, Los Alamitos (1987)
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was supported in part by NSF grants 0515313 and 0652601.
Rights and permissions
About this article
Cite this article
Harkins, R.C., Hitchcock, J.M. Dimension, Halfspaces, and the Density of Hard Sets. Theory Comput Syst 49, 601–614 (2011). https://doi.org/10.1007/s00224-010-9288-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00224-010-9288-1