Abstract
The event-uniform convergence of frequencies to probabilities is one of the main tools of the today theory of learning pattern recognition which enables one to substantiate the generalizability of the learning algorithms. Proposed was a new approach to derivation of the sufficient conditions for such convergence on the basis of only the topological properties of the event σ-algebra induced by the class under consideration.
Similar content being viewed by others
References
Vapnik, V.N. and Chervonenkis, A.Ya., Teoriya raspoznavaniya obrazov (Pattern Recognition Theory), Moscow: Nauka, 1974.
Vapnik, V.N., Statistical Learning Theory, New York: Wiley, 1998.
Pytkeev, E.G. and Khachai, M.Yu., Sigma-compactness of the Metric Boolean Algebras and Uniform Convergence of Frequencies to Probabilities, Tr. Inst. Mat. Mekh., 2010, vol. 16, no. 1, pp. 127–139.
Kadets, V.M., Kurs funktsional’nogo analiza (Course of Functional Analysis), Khar’kov: Khar’k. Natsional. Univ., 2006.
Borovkov, A.A., Matematicheskaya statistika (Mathematical Statistics), Novosibirsk: Nauka, 1997.
Bulinskii, A.V. and Shiryaev, A.N., Teoriya sluchainykh protsessov (Theory of Random Processes), Moscow: Fizmatlit, 2005.
Kosorok, M.R., Introduction to Empirical Processes and Semiparametric Inference, New York: Springer, 2008.
Author information
Authors and Affiliations
Additional information
Original Russian Text © E.G. Pytkeev, M.Yu. Khachai, 2012, published in Avtomatika i Telemekhanika, 2012, No. 2, pp. 89–98.
Rights and permissions
About this article
Cite this article
Pytkeev, E.G., Khachai, M.Y. Topological properties of measurable structures and sufficient conditions for uniform convergence of frequencies to probabilities. Autom Remote Control 73, 291–299 (2012). https://doi.org/10.1134/S0005117912020075
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117912020075