A sharp nonasymptotic bound and phase diagram of L
1/2 regularization |
| |
Authors: | Hai Zhang Zong Ben Xu Yao Wang Xiang Yu Chang Yong Liang |
| |
Institution: | 1. Department of Mathematics, Northwest University, Xi’an, 710069, P. R. China 2. Institute for Information and System Science, Xi’an Jiaotong University, Xi’an, 710049, P. R. China 3. Faculty of Information Technology and State Key Laboratory of Quality Research in Chinese Medicines, University of Science and Technology, Ma’cau, 999078, P. R. China
|
| |
Abstract: | We derive a sharp nonasymptotic bound of parameter estimation of the L 1/2 regularization. The bound shows that the solutions of the L 1/2 regularization can achieve a loss within logarithmic factor of an ideal mean squared error and therefore underlies the feasibility and effectiveness of the L 1/2 regularization. Interestingly, when applied to compressive sensing, the L 1/2 regularization scheme has exhibited a very promising capability of completed recovery from a much less sampling information. As compared with the L p (0 < p < 1) penalty, it is appeared that the L 1/2 penalty can always yield the most sparse solution among all the L p penalty when 1/2 ≤ p< 1, and when 0 < p< 1/2, the L p penalty exhibits the similar properties as the L 1/2 penalty. This suggests that the L 1/2 regularization scheme can be accepted as the best and therefore the representative of all the L p (0 < p< 1) regularization schemes. |
| |
Keywords: | L/ regularization phase diagram compressive sensing |
本文献已被 CNKI 维普 SpringerLink 等数据库收录! |
|