TY - GEN
T1 - Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
AU - Shnlev-Shwartz, Shai
AU - Zhang, Tong
PY - 2014
Y1 - 2014
N2 - 2014 We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runtime of the framework and obtain rates that improve state- of-the-art results for various key machine learning optimization problems including SVM, logistic regression, ridge regression. Lasso. and multi- class SVM. Experiments validate our theoretical findings.
AB - 2014 We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runtime of the framework and obtain rates that improve state- of-the-art results for various key machine learning optimization problems including SVM, logistic regression, ridge regression. Lasso. and multi- class SVM. Experiments validate our theoretical findings.
UR - http://www.scopus.com/inward/record.url?scp=84919796368&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84919796368&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84919796368
T3 - 31st International Conference on Machine Learning, ICML 2014
SP - 111
EP - 119
BT - 31st International Conference on Machine Learning, ICML 2014
PB - International Machine Learning Society (IMLS)
T2 - 31st International Conference on Machine Learning, ICML 2014
Y2 - 21 June 2014 through 26 June 2014
ER -