Statistical performance of Support Vector Machines

Statistical performance of Support Vector Machines (2004)

Cached

Download Links

[www-connex.lip6.fr]

by Gilles Blanchard , Olivier Bousquet , Pascal Massart

Citations:

30 - 6 self

BibTeX

@TECHREPORT{Blanchard04statisticalperformance,
    author = {Gilles Blanchard and Olivier Bousquet and Pascal Massart},
    title = {Statistical performance of Support Vector Machines},
    institution = {},
    year = {2004}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

Abstract The "Support Vector Machine " algorithm is well known to the computer learningcommunity for its very good practical results. The goal of the present paper to study this algorithm from a statistical perspective, using tools of concentration theory and empiricalprocesses.

Citations

1512	Smola A: Learning with Kernels - Schölkopf - 2002
207	Probability in Banach spaces - Ledoux, Talagrand - 1991
185	Rademacher and gaussian complexities: Risk bounds and structural - Bartlett, Mendelson - 2002
175	Scale-sensitive dimensions, uniform convergence, and learnability - Alon, Ben-David, et al. - 1997
156	The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network - Bartlett
124	Stability and generalization - Bousquet, Elisseeff - 2002
104	On the influence of the kernel on the consistency of support vector machines - Steinwart - 2001
100	Optimal aggregation of classifiers in statistical learning - Tsybakov
90	Empirical margin distributions and bounding the generalization error of combined classifiers - Koltchinskii, Panchenko - 2002
85	Statistical behavior and consistency of classification methods based on convex risk minimization. The Annals of Statistics - Zhang
63	Some applications of concentration inequalities to Statistics. Ann. Fac. Sciences de Toulouse IX - MASSART - 2000
36	On the rate of convergence of regularized boosting classifiers - Blanchard, Vayatis
35	A Bennett concentration inequality and its application to suprema of empirical processes - Bousquet - 2002
34	Improving the sample complexity using global data - Mendelson - 2002
25	Risk bounds for statistical learning - Massart, Nédélec - 2006
19	Generalization bounds via eigenvalues of the gram matrix - Schölkopf, Shawe-Taylor, et al. - 1999
6	Surveys in Combinatorics, chapter On the method of bounded differences - McDiarmid - 1989
2	About the constants in Talagrand's inequality for empirical processes, The Annals of Probability 29 - Massart - 2000
1	Local Rademacher complexities, 2002 - Bartlett, Bousquet, et al. - 2003