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

arXiv: https://arxiv.org/abs/1408.2714 · HTML: https://mlsanity.com/paper/1408.2714/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2014.

## Built on by (most cited first, 3 of 3)

- [Adaptive Group Lasso Neural Network Models for Functions of Few Variables and Time-Dependent Data](https://mlsanity.com/paper/2108.10825/) (2021)
- [Posterior concentration and fast convergence rates for generalized Bayesian learning](https://mlsanity.com/paper/2111.10243/) (2021)
- [A Generalization Bound of Deep Neural Networks for Dependent Data](https://mlsanity.com/paper/2310.05892/) (2023)

## Abstract (arXiv)

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.