摘要
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.
| 源语言 | 英语 |
|---|---|
| 页（从-至） | 1586-1595 |
| 页数 | 10 |
| 期刊 | Advances in Neural Information Processing Systems |
| 卷 | 2018-December |
| 出版状态 | 已出版 - 2018 |
| 已对外发布 | 是 |
| 活动 | 32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, 加拿大 期限: 2 12月 2018 → 8 12月 2018 |
指纹
探究 'Multi-class learning: From theory to algorithm' 的科研主题。它们共同构成独一无二的指纹。引用此
Li, J., Liu, Y., Yin, R., Zhang, H., Ding, L., & Wang, W. (2018). Multi-class learning: From theory to algorithm. Advances in Neural Information Processing Systems, 2018-December, 1586-1595.