1. NCCU Academic Hub
  2. 學術產出
  3. 商學院
  4. 會議論文
  5. Item

學術產出-會議論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Trust region Newton methods for large-scale logistic regression
作者 Lin, C.-J.;Weng, Ruby Chiu-Hsing;Keerthi, S.S.
翁久幸
貢獻者 統計系
關鍵詞 Approximation algorithms; Classification (of information); Convergence of numerical methods; Mathematical models; Natural language processing systems; Regression analysis; Logistic regression; Quasi Newton approach; Newton-Raphson method
日期 2007
上傳時間 13-七月-2015 15:16:50 (UTC+8)
摘要 Large-scale logistic regression arises in many applications such as document classification and natural language processing. In this paper, we apply a trust region Newton method to maximize the log-likelihood of the logistic regression model. The proposed method uses only approximate Newton steps in the beginning, but achieves fast convergence in the end. Experiments show that it is faster than the commonly used quasi Newton approach for logistic regression. We also compare it with linear SVM implementations.
關聯 ACM International Conference Proceeding Series,Volume 227, Pages 561-568
24th International Conference on Machine Learning, ICML 2007,20 June 2007 through 24 June 2007,Corvalis, OR
資料類型 conference
DOI http://dx.doi.org/10.1145/1273496.1273567
dc.contributor 統計系-
dc.creator (作者) Lin, C.-J.;Weng, Ruby Chiu-Hsing;Keerthi, S.S.-
dc.creator (作者) 翁久幸-
dc.date (日期) 2007-
dc.date.accessioned 13-七月-2015 15:16:50 (UTC+8)-
dc.date.available 13-七月-2015 15:16:50 (UTC+8)-
dc.date.issued (上傳時間) 13-七月-2015 15:16:50 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/76496-
dc.description.abstract (摘要) Large-scale logistic regression arises in many applications such as document classification and natural language processing. In this paper, we apply a trust region Newton method to maximize the log-likelihood of the logistic regression model. The proposed method uses only approximate Newton steps in the beginning, but achieves fast convergence in the end. Experiments show that it is faster than the commonly used quasi Newton approach for logistic regression. We also compare it with linear SVM implementations.-
dc.format.extent 176 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) ACM International Conference Proceeding Series,Volume 227, Pages 561-568-
dc.relation (關聯) 24th International Conference on Machine Learning, ICML 2007,20 June 2007 through 24 June 2007,Corvalis, OR-
dc.subject (關鍵詞) Approximation algorithms; Classification (of information); Convergence of numerical methods; Mathematical models; Natural language processing systems; Regression analysis; Logistic regression; Quasi Newton approach; Newton-Raphson method-
dc.title (題名) Trust region Newton methods for large-scale logistic regression-
dc.type (資料類型) conferenceen
dc.identifier.doi (DOI) 10.1145/1273496.1273567-
dc.doi.uri (DOI) http://dx.doi.org/10.1145/1273496.1273567-