Covering number bounds of certain regularized linear function classes
作者： Tong Zhang
DOI: 10.1162/153244302760200713
关键词:
摘要: … covering number bounds, which complement and improve results from previous studies. In our analysis, we emphasize the importance of covering number … original d-dimensional space …
acm.org
crossref.org参考文章(38)
Michel Ledoux, Michel Talagrand, Probability in Banach spaces ,(1991)
Tong Zhang, On the Dual Formulation of Regularized Linear Systems with Convex Risks Machine Learning. ,vol. 46, pp. 91- 129 ,(2002) , 10.1023/A:1012498226479
Peter Bartlett, Martin M. Anthony, Learning in Neural Networks: Theoretical Foundations Cambridge University Press. ,(1999)
Shahar Mendelson, Geometric Methods in the Analysis of Glivenko-Cantelli Classes european conference on computational learning theory. pp. 256- 272 ,(2001) , 10.1007/3-540-44581-1_17
Martin Anthony, Peter L Bartlett, Peter L Bartlett, Neural Network Learning: Theoretical Foundations ,(1999)
Bernhard Schölkopf, Alex J. Smola, Robert C. Williamson, Entropy Numbers of Linear Function Classes conference on learning theory. pp. 309- 319 ,(2000) , 10.5555/648299.761588
Nello Cristianini, John Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods ,(2000)
László Györfi, Luc Devroye, Gábor Lugosi, A Probabilistic Theory of Pattern Recognition ,(1996)
Peter Bartlett, John Shawe-Taylor, Generalization performance of support vector machines and other pattern classifiers Advances in kernel methods. pp. 43- 54 ,(1999)
R. M. Dudley, A course on empirical processes Springer Berlin Heidelberg. pp. 1- 142 ,(1984) , 10.1007/BFB0099432