Multi-Class Learning: From Theory to Algorithm

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.

Authors

• Jian Li Tencent Hunyuan
• Yong Liu
• Rong Yin Institute of Information Engineering, CAS School of Cyber Security, University of Chinese Academy of Sciences
• Hua Zhang Texas A&M University-Corpus Christi
• Lizhong Ding
• Weiping Wang Institute of Information Engineering, Chinese Academy of Sciences

Keywords

No keywords are indexed for this paper.