Abstract
We considerStability—( Learnability—( the fundamental question of learnability of a hypothesis class in the supervised learningSupervised learning setting and in the general learningGeneral learning setting introduced by Vladimir Vapnik. We survey classic results characterizing learnability in terms of suitable notions of complexity, as well as more recent results that establish the connection between learnability and stability of a learning algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
ConsistencyConsistency can be defined with respect to other convergence notions for random variables. If the loss function is bounded, convergence in probability is equivalent to convergence in expectation.
- 2.
We say that a learning algorithm A is symmetric if it does not depend on the order of the points in z n .
- 3.
Note that this construction is not possible in classification or in regression with the square loss.
References
Alon, N., Ben-David, S., Cesa-Bianchi, N., Haussler, D.: Scale-sensitive dimensions, uniform convergence, and learnability. J. ACM 44(4), 615–631 (1997)
Anthony, M., Bartlett, P.L.: Neural network learning: theoretical foundations. Cambridge University Press, Cambridge (1999)
Bartlett, P., Long, P., Williamson, R.: Fat-shattering and the learnability of real-valued functions. J. Comput. Syst. Sci. 52, 434–452 (1996)
Bousquet, O., Elisseeff, A.: Stability and generalization. J. Mach. Learn. Res. 2, 499–526 (2002)
Daniely, A., Sabato, S., Ben-David, S., Shalev-Shwartz, S.: Multiclass learnability and the ERM principle. J. Mach. Learn. Res. Proc. Track 19, 207–232 (2011)
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Applications of Mathematics 31. Springer, New York (1996)
Dudley, R., Giné, E., Zinn, J.: Uniform and universal Glivenko-Cantelli classes. J. Theor. Prob. 4, 485–510 (1991)
Engl, H.W., Hanke, M., Neubauer, A.: Regularization of Inverse Problems. Mathematics and Its Applications, vol. 375. Kluwer, Dordrecht (1996)
Kearns, M.J., Schapire, R.E.: Efficient distribution-free learning of probabilistic concepts. In: Computational Learning Theory and Natural Learning Systems. Bradford Books, vol. I, pp. 289–329. MIT, Cambridge (1994)
Kutin, S., Niyogi, P.: Almost-everywhere algorithmic stability and generalization error. Technical report TR-2002-03, Department of Computer Science, The University of Chicago (2002)
Mukherjee, S., Niyogi, P., Poggio, T., Rifkin, R.: Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization. Adv. Comput. Math. 25(1–3), 161–193 (2006)
Poggio, T., Rifkin, R., Mukherjee, S., Niyogi, P.: General conditions for predictivity in learning theory. Nature 428, 419–422 (2004)
Rakhlin, A., Sridharan, K., Tewari, A.: Online learning: beyond regret. J. Mach. Learn. Res. Proc. Track 19, 559–594 (2011)
Shalev-Shwartz, S., Shamir, O., Srebro, N., Sridharan, K.: Learnability, stability and uniform convergence. J. Mach. Learn. Res. 11, 2635–2670 (2010)
Steinwart, I., Christmann, A.: Support Vector Machines. Information Science and Statistics. Springer, New York (2008)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Vapnik, V.N., Chervonenkis, A.Y.: Theory of uniform convergence of frequencies of events to their probabilities and problems of search for an optimal solution from empirical data. Avtomatika i Telemekhanika 2, 42–53 (1971)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Villa, S., Rosasco, L., Poggio, T. (2013). On Learnability, Complexity and Stability. In: Schölkopf, B., Luo, Z., Vovk, V. (eds) Empirical Inference. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41136-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-41136-6_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41135-9
Online ISBN: 978-3-642-41136-6
eBook Packages: Computer ScienceComputer Science (R0)