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.
Keywords
Cite
@article{arxiv.1408.2714,
title = {Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers},
author = {Vu Dinh and Lam Si Tung Ho and Nguyen Viet Cuong and Duy Nguyen and Binh T. Nguyen},
journal= {arXiv preprint arXiv:1408.2714},
year = {2015}
}
Comments
12th Annual Conference on Theory and Applications of Models of Computation (TAMC 2015)