Abstract
In this paper we investigate the problem of active learning the partition of the n-dimensional hypercube into m cubes, where the i-th cube has color i. The model we are using is exact learning via color evaluation queries, without equivalence queries, as proposed by the work of Fine and Mansour. We give a randomized algorithm solving this problem in O(mlogn) expected number of queries, which is tight, while its expected running time is O(m 2 n logn).
Furthermore, we generalize the problem to allow partitions of the cube into m monochromatic parts, where each part is the union of p cubes. We give two randomized algorithms for the generalized problem. The first uses O(m p 2 2plogn) expected number of queries, which is almost tight with the lower bound. However, its naïve implementation requires an exponential running time in n. The second, more practical, algorithm achieves a better running time complexity of \(\tilde{O}(m^2 n^2 2^{2^p})\). However, it may fail to learn the correct partition with an arbitrarily small probability and it requires slightly more expected number of queries: \(\tilde{O}(mn 4^p)\), where the \(\tilde{O}\) represents a poly logarithmic factor in m,n,2p.
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
Beimel, A., Bergadano, F., Bshouty, N.H., Kushilevitz, E., Varricchio, S.: Learning functions represented as multiplicity automata. J. ACM 47(3), 506–530 (2000)
Bshouty, N.H., Goldman, S.A., Hancock, T.R., Matar, S.: Asking questions to minimize errors. J. Comput. Syst. Sci. 52(2), 268–286 (1996)
Blum, A., Rudich, S.: Fast learning of k-term dnf formulas with queries. In: STOC 1992: Proceedings of the twenty-fourth annual ACM symposium on Theory of computing, pp. 382–389. ACM, New York (1992)
Bshouty, N.H.: Exact learning boolean functions via the monotone theory. Inf. Comput. 123(1), 146–153 (1995)
Bshouty, N.H.: Simple learning algorithms using divide and conquer. Comput. Complex 6(2), 174–194 (1997)
Chandra, A.K., Markowsky, G.: On the number of prime implicants. Discrete Mathematics 24(1), 7–11 (1978)
Downey, R.G., Fellows, M.R.: Parameterized Complexity. Springer, Heidelberg (1999)
Feldman, V.: Attribute-efficient and non-adaptive learning of parities and dnf expressions. J. Mach. Learn. Res. 8, 1431–1460 (2007)
Fine, S., Mansour, Y.: Active sampling for multiple output identification. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, pp. 620–634. Springer, Heidelberg (2006)
Hellerstein, L., Raghavan, V.: Exact learning of dnf formulas using dnf hypotheses. J. Comput. Syst. Sci. 70(4), 435–470 (2005)
Jackson, J.C.: An efficient membership-query algorithm for learning DNF with respect to the uniform distribution. In: IEEE Symposium on Foundations of Computer Science, pp. 42–53 (1994)
Jukna, S., Razborov, A., Savicky, P., Wegener, I.: On p versus NP ∩ co-NP for decision trees and read-once branching programs. Electronic Colloquium on Computational Complexity (ECCC) 4(023) (1997)
Kalai, A.T.: Learning nested halfspaces and uphill decision trees. In: Bshouty, N.H., Gentile, C. (eds.) COLT. LNCS (LNAI), vol. 4539, pp. 378–392. Springer, Heidelberg (2007)
Kushilevitz, E., Mansour, Y.: Learning decision trees using the fourier spectrum. In: STOC 1991: Proceedings of the twenty-third annual ACM symposium on Theory of computing, pp. 455–464. ACM, New York (1991)
Kleitman, D., Spencer, J.: Families of k-independent sets. Discrete Math. 6, 255–262 (1973)
Kushilevitz, E.: A simple algorithm for learning o (log n)-term dnf. Inf. Process. Lett. 61(6), 289–292 (1997)
Kearns, M.J., Vazirani, U.V.: An Introduction to Computational Learning Theory. MIT Press, Cambridge (1994)
Murthy, S.K.: Automatic construction of decision trees from data: A multi-disciplinary survey. Data Mining and Knowledge Discovery 2(4), 345–389 (1998)
Safavin, S.R., Langrebe, D.: A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man and Cybernetics 21, 660–674 (1991)
Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134–1142 (1984)
Wile, B., Goss, J., Roesner, W.: Comprehensive Functional Verification: The Complete Industry Cycle (Systems on Silicon). Morgan Kaufmann Publishers Inc., San Francisco (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hoory, S., Margalit, O. (2008). Finding the Rare Cube. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2008. Lecture Notes in Computer Science(), vol 5254. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87987-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-87987-9_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87986-2
Online ISBN: 978-3-540-87987-9
eBook Packages: Computer ScienceComputer Science (R0)