Abstract
We study learning in a modified EXACT model, where the oracles are corrupt and only few of the presented attributes are relevant. Both modifications were already studied in the literature, and efficient solutions were found to most of their variants. Nonetheless, their reasonable combination is yet to be studied, and combining the existing solutions either fails or works with complexity that can be significantly improved. In this paper we prove equivalence of EXACT learning attribute-efficiently with and without corrupt oracles. For each of the possible scenarios we describe a generic scheme that enables learning in these cases using modifications of the standard learning algorithms. We also generalize and improve previous non attribute-efficient algorithms for learning with corrupt oracles.
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
Angluin, D.: Queries and Concept Learning. Machine Learning 2(4), 319–342 (1987)
Angluin, D., Hellerstein, L., Karpinski, M.: Learning read-once formulas with queries. J. ACM 40(1), 185–210 (1993)
Angluin, D., Krikis, M.: Learning with malicious membership queries and exceptions (extended abstract). In: COLT 1994: Proceedings of the seventh annual conference on Computational learning theory, pp. 56–57. ACM Press, New York (1994)
Angluin, D., Krikis, M., Sloan, R.H., Turán, G.: Malicious omissions and errors in answers to membership queries. Machine Learning 28, 211–255 (1997)
Angluin, D., Laird, P.: Learning From Noisy Examples. Machine Learning 2(4), 343–370 (1988)
Auer, P., Cesa-Bianchi, N.: On-Line Learning with Malicious Noise and the Closure Algorithm. Ann. Math. Artif. Intell. 23(1-2), 83–99 (1998)
Auer, P., Long, P.M.: Simulating Access to Hidden Information while Learning. Electronic Colloquium on Computational Complexity (ECCC) 7(67) (2000)
Bisht, L., Bshouty, N.H., Khoury, L.: Learning with Errors in Answers to Membership Queries (Extracted Abstract). In: FOCS 2004: Proceedings of the 45th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2004), pp. 611–620. IEEE Computer Society, Los Alamitos (2004)
Blum, Hellerstein, Littlestone: Learning in the Presence of Finitely or Infinitely Many Irrelevant Attributes (Extended Abstract). In: COLT: Proceedings of the Workshop on Computational Learning Theory. Morgan Kaufmann Publishers, San Francisco (1991)
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. In: Proceedings of the eighth annual conference on Computational learning theory, pp. 447–453. ACM Press, New York (1995)
Bshouty, N.H., Hellerstein, L.: Attribute-Efficient Learning in Query and Mistake-Bound Models. journal = ”Journal of Computer and System Sciences 56(3), 310–319 (1998)
Littlestone, N.: Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm. Machine Learning 2(4), 285–318 (1988)
Sakakibara, Y.: On learning from queries and counterexamples in the presence of noise. Inf. Process. Lett. 37(5), 279–284 (1991)
Sloan, R.H., Turan, G.: Learning with Queries but Incomplete Information (Extended Abstract). In: Computational Learing Theory, pp. 237–245 (1994)
Valiant, L.G.: A Theory of the Learnable. Commun. ACM 27(11), 1134–1142 (1984)
Valiant., L.G.: Projection learning. In: Proceedings of the eleventh annual conference on Computational learning theory, pp. 278–293. ACM Press, New York (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bennet, R., Bshouty, N.H. (2005). Learning Attribute-Efficiently with Corrupt Oracles. In: Jain, S., Simon, H.U., Tomita, E. (eds) Algorithmic Learning Theory. ALT 2005. Lecture Notes in Computer Science(), vol 3734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564089_16
Download citation
DOI: https://doi.org/10.1007/11564089_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29242-5
Online ISBN: 978-3-540-31696-1
eBook Packages: Computer ScienceComputer Science (R0)