Multi-Class Learning: From Theory to Algorithm

Abstract

In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis. The theoretical analysis motivates us to devise two effective multi-class kernel learning algorithms with statistical guarantees. Experimental results show that our proposed methods can significantly outperform the existing multi-class classification methods.

Cite

Text

Li et al. "Multi-Class Learning: From Theory to Algorithm." Neural Information Processing Systems, 2018.

Markdown

[Li et al. "Multi-Class Learning: From Theory to Algorithm." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/li2018neurips-multiclass/)

BibTeX

@inproceedings{li2018neurips-multiclass,
  title     = {{Multi-Class Learning: From Theory to Algorithm}},
  author    = {Li, Jian and Liu, Yong and Yin, Rong and Zhang, Hua and Ding, Lizhong and Wang, Weiping},
  booktitle = {Neural Information Processing Systems},
  year      = {2018},
  pages     = {1586-1595},
  url       = {https://mlanthology.org/neurips/2018/li2018neurips-multiclass/}
}