Thresholded spectral algorithms for sparse approximations
- 点击量:
- 作者：Zheng-Chu Guo
- 所属单位：数理与信息工程学院
- 文献类型：期刊
- 发表时间：2017-01-01
- 发表刊物：Analysis and Applications
- 卷号：Vol.15
- 期号：No.3
- 页面范围：433
- Issn号：0219-5305;1793-6861
- 是否译文：否
- 关键字：Learning theory; thresholded spectral algorithm; sparsity; learning rate
- 摘要：Spectral algorithms form a general framework that unifies many regularization schemes in learning theory. In this paper, we propose and analyze a class of thresholded spectral algorithms that are designed based on empirical features. Soft thresholding is
推荐此文
