Timezone: »

 
Poster
Multi-Class Learning: From Theory to Algorithm
Jian Li · Yong Liu · Rong Yin · Hua Zhang · Lizhong Ding · Weiping Wang

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 210 #100
in Thu Poster Session B »

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.

Keywords: Learning Theory · Classification · Large Margin Methods

Author Information

Jian Li (Institute of Information Engineering, CAS)
Yong Liu (Institute of Information Engineering, CAS)
Rong Yin (School of Cyber Security, University of Chinese Academy of Sciences)
Hua Zhang (Institute of Information Engineering,Chinese Academy of Sciences)
Lizhong Ding (KAUST)
Weiping Wang (Institute of Information Engineering, CAS, China)

More from the Same Authors