Abstract
We consider the problem of proper learning a Boolean Halfspace with integer weights {0,1,…,t} from membership queries only. The best known algorithm for this problem is an adaptive algorithm that asks \(n^{O(t^5)}\) membership queries where the best lower bound for the number of membership queries is n t [4].
In this paper we close this gap and give an adaptive proper learning algorithm with two rounds that asks n O(t) membership queries. We also give a non-adaptive proper learning algorithm that asks \(n^{O(t^3)}\) membership queries.
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
Aigner, M.: Combinatorial Search. Wiley Teubner Series on Applicable Theory in Computer Science. Teubner, Stuttgart (1988)
Angluin, D.: Queries and Concept Learning. Machine Learning 2(4), 319–342 (1987)
Alon, A., Asodi, V.: Learning a Hidden Subgraph. SIAM J. Discrete Math. 18(4), 697–712 (2005)
Abboud, E., Agha, N., Bshouty, N.H., Radwan, N., Saleh, F.: Learning Threshold Functions with Small Weights Using Membership Queries. In: COLT 1999. pp. 318–322 (1999)
Alon, N., Beigel, R., Kasif, S., Rudich, S., Sudakov, B.: Learning a Hidden Matching. SIAM J. Comput. 33(2), 487–501 (2004)
Angluin, D., Chen, J.: Learning a Hidden Hypergraph. Journal of Machine Learning Research 7, 2215–2236 (2006)
Angluin, D., Chen, J.: Learning a hidden graph using O(log n) queries per edge. J. Comput. Syst. Sci. 74(4), 546–556 (2008)
Beigel, R., Alon, N., Kasif, S., Serkan Apaydin, M., Fortnow, L.: An optimal procedure for gap closing in whole genome shotgun sequencing. In: RECOMB 2001, pp. 22–30 (2001)
Biglieri, E., Gyorfi, L.: Multiple Access Channels: Theory and Practice. IOS Press (2007)
Bshouty, N.H.: Exact Learning from Membership Queries: Some Techniques, Results and New Directions. In: Jain, S., Munos, R., Stephan, F., Zeugmann, T. (eds.) ALT 2013. LNCS, vol. 8139, pp. 33–52. Springer, Heidelberg (2013)
Choi, S.-S., Kim, J.H.: Optimal query complexity bounds for finding graphs. Artif. Intell. 174(9-10), 551–569 (2010)
Chirkov, A.Y., Zolotykh, N.Y.: On the number of irreducible points in polyhedra arXiv:1306.4289
Grebinski, V., Kucherov, G.: Reconstructing a Hamiltonian Cycle by Querying the Graph: Application to DNA Physical Mapping. Discrete Applied Mathematics 88(1-3), 147–165 (1998)
Hegedüs, T.: Generalized teaching dimensions and the query complexity of learning. In: Proceedings of the 8th Annual ACM Conference on Computational Learning Theory (COLT 1995), pp. 108–117. ACM Press, New York (1995)
Ngo, H.Q., Du., D.-Z.: A Survey on Combinatorial Group Testing Algorithms with Applications to DNA Library Screening. DIMACS Series in Discrete Mathematics and Theoretical Computer Science
Shevchenko, V.N., Zolotykh, N.Y.: Lower Bounds for the Complexity of Learning Half-Spaces with Membership Queries. In: Richter, M.M., Smith, C.H., Wiehagen, R., Zeugmann, T. (eds.) ALT 1998. LNCS (LNAI), vol. 1501, pp. 61–71. Springer, Heidelberg (1998)
Zolotykh, N.Y., Shevchenko, V.N.: Deciphering threshold functions of k-valued logic. Discrete Analysis and Operations Research. Novosibirsk 2(3), 18–23 (1995); English transl.: Korshunov, A.D. (ed.): Operations Research and Discrete Analysis, pp. 321–326. Kluwer Ac. Publ., Netherlands (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Abasi, H., Abdi, A.Z., Bshouty, N.H. (2014). Learning Boolean Halfspaces with Small Weights from Membership Queries. In: Auer, P., Clark, A., Zeugmann, T., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2014. Lecture Notes in Computer Science(), vol 8776. Springer, Cham. https://doi.org/10.1007/978-3-319-11662-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-11662-4_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11661-7
Online ISBN: 978-3-319-11662-4
eBook Packages: Computer ScienceComputer Science (R0)