Learning from dependent observations

Steinwart, Ingo; Hush, Don; Scovel, Clint

Learning from dependent observations

Authors

Steinwart, Ingo

Hush, Don

Scovel, Clint

Description

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) essentially only require that the data-generating process satisfies a certain law of large numbers. We then consider the learnability of SVMs for $\a$-mixing (not necessarily stationary) processes for both classification and regression, where for the latter we explicitly allow unbounded noise.
submitted to Journal of Multivariate Analysis