Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers

Abstract

We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging drifting distribution. These are two typical scenarios where training data are not iid. The learning rates are obtained under a multiclass version of Tsybakov's margin assumption, a type of low-noise assumption, and do not depend on the number of classes. Our results are general and include a previous result for binary-class plug-in classifiers with iid data as a special case. In contrast to previous works for least squares SVMs under the binary-class setting, our results retain the optimal learning rate in the iid case.

arXiv comment12th Annual Conference on Theory and Applications of Models of Computation (TAMC 2015)

References in corpus (2)

• Fast rates for support vector machines using Gaussian kernels
• Analysis of comparative data with hierarchical autocorrelation