Research Area: Machine Learning
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:
Multi-Class Learning
Machine Learning
Deep Learning
Author(s) Name: Jian Li, Yong Liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang
Journal name: Advances in Neural Information Processing Systems
Conferrence name:
Publisher name: NeurIPS Proceedings
DOI:
Volume Information:
