Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers
This work addresses the challenge of non-iid data in machine learning, providing theoretical guarantees for multiclass classification, but it is incremental as it extends existing binary-class results to multiclass settings.
The paper tackles the problem of learning from non-iid data by proving new fast learning rates for one-vs-all multiclass plug-in classifiers under Tsybakov's margin assumption, with results that do not depend on the number of classes and retain optimal rates in the iid case.
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.