Title :
Least-Square Regularized Regression in Compressed Domain
Author :
Lu, Weijun ; Tang, Yi ; Chen, Hong
Author_Institution :
Sch. of Comput. Sci., Wuhan Univ. of Sci. & Eng., Wuhan, China
Abstract :
This paper considers the regularized learning algorithm associated with the least-square loss and compressed domain. The target is the error analysis for the regression problem learned in compressed domain. We show that the least-square regularized algorithm is beneficial from the compressed sensing.
Keywords :
data compression; error analysis; learning (artificial intelligence); regression analysis; compressed domain; error analysis; least-square regression method; loss domain; regularized learning algorithm; Algorithm design and analysis; Complexity theory; Compressed sensing; Distortion measurement; Machine learning; Presses; Training; compressed learning; least square regression; sparsity;
Conference_Titel :
Intelligence Information Processing and Trusted Computing (IPTC), 2010 International Symposium on
Conference_Location :
Huanggang
Print_ISBN :
978-1-4244-8148-4
Electronic_ISBN :
978-0-7695-4196-9
DOI :
10.1109/IPTC.2010.27
