Classification with non-i.i.d. sampling

β-mixing sequence Reproducing kernel Hilbert spaces ℓ 2-empirical covering number Capacity dependent error bounds a b s t r a c t We study learning algorithms for classification generated by regularization schemes in reproducing kernel Hilbert spaces associated with a general convex loss function in a non-i.i.d. process. Error analysis is studied and our main purpose is to provide an elaborate capacity dependent error bounds by applying concentration techniques involving the ℓ 2-empirical covering numbers.