Abstract
The Statistical Query model was introduced in [6] to handle noise in the well-known PAC model. In this model the learner gains information about the target concept by asking for various statistics about it. Characterizing the number of queries required by learning a given concept class under fixed distribution was already considered in [3] for weak learning; then in [8] strong learnability was also characterized. However, the proofs for these results in [3,10,8] (and for strong learnability even the characterization itself) are rather complex; our main goal is to present a simple approach that works for both problems. Additionally, we strengthen the result on strong learnability by showing that a class is learnable with polynomially many queries iff all consistent algorithms use polynomially many queries, and by showing that proper and improper learning are basically equivalent. As an example, we apply our results on conjunctions under the uniform distribution.
This work was supported in part by the Deutsche Forschungsgemeinschaft Grant SI 498/8-1, and the NKTH grant of the National Technology Programme 2008 (project codename AALAMSRK NTP OM-00192/2008) of the Hungarian government.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aslam, J.A., Decatur, S.E.: General bounds on statistical query learning and PAC learning with noise via hypothesis boosting. Inf. Comput. 141(2), 85–118 (1998)
Ben-David, S., Itai, A., Kushilevitz, E.: Learning by distances. Inform. Comput. 117(2), 240–250 (1995)
Blum, A., Furst, M., Jackson, J., Kearns, M., Mansour, Y., Rudich, S.: Weakly learning DNF and characterizing statistical query learning using fourier analysis. In: Proc. of 26th ACM Symposium on Theory of Computing (1994)
Bshouty, N.H., Feldman, V.: On using extended statistical queries to avoid membership queries. Journal of Machine Learning Research 2, 359–395 (2002)
Feldman, V.: A complete characterization of statistical query learning with applications to evolvability. In: FOCS 2009 (to appear, 2009)
Kearns, M.: Efficient noise-tolerant learning from statistical queries. J. ACM 45(6), 983–1006 (1998)
Köbler, J., Lindner, W.: The complexity of learning concept classes with polynomial general dimension. Theor. Comput. Sci. 350(1), 49–62 (2006)
Simon, H.U.: A characterization of strong learnability in the statistical query model. In: Thomas, W., Weil, P. (eds.) STACS 2007. LNCS, vol. 4393, pp. 393–404. Springer, Heidelberg (2007)
Szörényi, B.: Honest queries do not help in the statistical query model (manuscript)
Yang, K.: New lower bounds for statistical query learning. J. Comput. Syst. Sci. 70(4), 485–509 (2005); In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 229–509. Springer, Heidelberg (2002)
Yang, K.: On learning correlated boolean functions using statistical queries. In: Abe, N., Khardon, R., Zeugmann, T. (eds.) ALT 2001. LNCS (LNAI), vol. 2225, pp. 59–76. Springer, Heidelberg (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Szörényi, B. (2009). Characterizing Statistical Query Learning: Simplified Notions and Proofs. In: Gavaldà, R., Lugosi, G., Zeugmann, T., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2009. Lecture Notes in Computer Science(), vol 5809. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04414-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-04414-4_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04413-7
Online ISBN: 978-3-642-04414-4
eBook Packages: Computer ScienceComputer Science (R0)