https://scholars.lib.ntu.edu.tw/handle/123456789/406503
標題: | Estimation error of the constrained lasso. | 作者: | Zerbib, Nissim Yen-Huan Li Hsieh, Ya-Ping Cevher, Volkan |
公開日期: | 2016 | 起(迄)頁: | 433-438 | 來源出版物: | 54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016 | 摘要: | This paper presents a non-asymptotic upper bound for the estimation error of the constrained lasso, under the high-dimensional (n ≪ p) setting. In contrast to existing results, the error bound in this paper is sharp, is valid when the parameter to be estimated is not exactly sparse (e.g., when it is weakly sparse), and shows explicitly the effect of overestimating the ℓ1-norm of the parameter to be estimated on the estimation performance. The results of this paper show that the constrained lasso is minimax optimal for estimating a parameter with bounded ℓ1-norm, and also for estimating a weakly sparse parameter if its ℓ1-norm is accessible. © 2016 IEEE. |
描述: | Monticello, IL, USA |
URI: | https://doi.org/10.1109/ALLERTON.2016.7852263 https://scholars.lib.ntu.edu.tw/handle/123456789/406503 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85015222060&doi=10.1109%2fALLERTON.2016.7852263&partnerID=40&md5=28147d0e44fcb23e624d9df6953bcc2a |
DOI: | 10.1109/ALLERTON.2016.7852263 | SDG/關鍵字: | Errors; Estimation; Error bound; Estimation errors; Estimation performance; High-dimensional; Minimax; Non-asymptotic; Upper Bound; Parameter estimation |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。