论文信息 - Bayesian approach, theory of empirical risk minimization. Comparative analysis

Bayesian approach, theory of empirical risk minimization. Comparative analysis

Error estimates of empirical-risk minimization methods for an infinite number of decision rules are analyzed. Optimal deterministic estimates of the error of the Bayesian classification procedure for independent features are obtained based on averaging over a great number of training samples as a control. For the Boolean case, the Bayesian procedure is equivalent to a classification procedure based on a separating hyperplane.

[1] I. V. Sergienko,et al. Complexity of classification problems , 1996 .

[2] I. V. Sergienko,et al. Efficiency of Bayesian classification procedure , 1995 .

[3] Michel Loève,et al. Probability Theory I , 1977 .

[4] M. Kline. Mathematics: The Loss of Certainty , 1982 .

[5] I. V. Sergienko,et al. Design principles for inductive inference procedures , 2006 .

[6] I. V. Sergienko,et al. Predicting protein secondary structure based on Bayesian classification procedures on Markovian chains , 2007 .

[7] S. Boucheron,et al. Theory of classification : a survey of some recent advances , 2005 .

[8] Alexandra A. Vagis,et al. Complexity of Bayesian Procedure of Inductive Inference. Discrete Case , 2006 .

[9] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[10] Vladimir Vapnik,et al. Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics) , 1982 .

[11] V. Vapnik. Estimation of Dependences Based on Empirical Data , 2006 .

[12] I. V. Sergienko,et al. Optimal pattern recognition procedures and their application , 2007 .