NeurIPS 2018poster58 citations

Multi-Class Learning: From Theory to Algorithm

Jian Li, Yong Liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang

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.

BibTeX
@inproceedings{NEURIPS2018_1141938b,
 author = {Li, Jian and Liu, Yong and Yin, Rong and Zhang, Hua and Ding, Lizhong and Wang, Weiping},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Multi-Class Learning: From Theory to Algorithm},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/1141938ba2c2b13f5505d7c424ebae5f-Paper.pdf},
 volume = {31},
 year = {2018}
}
Multi-Class Learning: From Theory to Algorithm · NeurIPS 2018