The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 53-457
Full Name: Sheng Baohuai
Position: Professor
Age: ON
Sex: Male
Address: Department of Mathematics,Shaoxing College of Arts and Sciences,Shaoxing,Zhejiang,312000
Country: CHINA
Tel: 0861-0575-88345092
Tel prefix: 0861-0575-88056935
Fax: 0861-0575-88341826
E-mail address: bhsheng@usx.edu.cn
Other E-mails: shengbaohuai@163.com
Title of the Paper: Bound the Learning Rates with Generalized Gradients
Authors as they appear in the Paper: Sheng Baohuai;Xiang Daohong
Email addresses of all the authors: bhsheng@usx.edu.cn,shengbaohuai@163.com,daohongxiang@gmail.com
Number of paper pages: 10
Abstract: This paper considers the error bounds for the coefficient regularized regression scheme associated with Lipschitz loss. Our main goal is to study the convergence rates for this algorithm with non-smooth analysis. We give an explicit expression of the solution by means of generalized gradient of the loss which induces a capacity independent bound for the sample error. A kind of approximation error is provided with possibility theory.
Keywords: Regularization regression, Non-smooth analysis,Lipschitz loss,Machine learning,Learning rates.
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Machine learning
IP ADDRESS: 61.175.244.120
