Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1146853 | Journal of Multivariate Analysis | 2009 | 20 Pages |
Abstract
In most papers establishing consistency for learning algorithms it is assumed that the observations used for training are realizations of an i.i.d. process. In this paper we go far beyond this classical framework by showing that support vector machines (SVMs) only require that the data-generating process satisfies a certain law of large numbers. We then consider the learnability of SVMs for α-mixing (not necessarily stationary) processes for both classification and regression, where for the latter we explicitly allow unbounded noise.
Related Topics
Physical Sciences and Engineering
Mathematics
Numerical Analysis
Authors
Ingo Steinwart, Don Hush, Clint Scovel,