论文信息 - A framework for structural risk minimisation

A framework for structural risk minimisation

The paper introduces a framework for studying structural risk minimisation. The model views structural risk minimisation in a PAC context. It then considers the more general case when the hierarchy of classes is chosen in response to the data. This theoretically explains the impressive performance of the maximal margin hyperplane algorithm of Vapnik. It may also provide a general technique for exploitingserendipitous simplicity in observed data to obtain better prediction accuracy from small training sets.

[1] John B. Shoven,et al. I , Edinburgh Medical and Surgical Journal.

[2] Vladimir Vapnik,et al. Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[3] D. Pollard. Convergence of stochastic processes , 1984 .

[4] Nathan Linial,et al. Results on learnability and the Vapnik-Chervonenkis dimension , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[5] Bernhard E. Boser,et al. A training algorithm for optimal margin classifiers , 1992, COLT '92.

[6] N. Alon,et al. Scale-sensitive Dimensions, Uniform Convergence, , 1993 .

[7] John Shawe-Taylor,et al. A Result of Vapnik with Applications , 1993, Discrete Applied Mathematics.

[8] Vladimir Naumovich Vapni. The Nature of Statistical Learning Theory , 1995 .

[9] Noga Alon,et al. Scale-sensitive dimensions, uniform convergence, and learnability , 1997, JACM.