Semi-Stochastic Frank-Wolfe Algorithms with Away-Steps for Block-Coordinate Structure Problems
From MaRDI portal
Publication:6270109
arXiv1602.01543MaRDI QIDQ6270109FDOQ6270109
Authors: Donald Goldfarb, G. Iyengar, Chaoxu Zhou 
Publication date: 3 February 2016
Abstract: We propose a semi-stochastic Frank-Wolfe algorithm with away-steps for regularized empirical risk minimization and extend it to problems with block-coordinate structure. Our algorithms use adaptive step-size and we show that they converge linearly in expectation. The proposed algorithms can be applied to many important problems in statistics and machine learning including regularized generalized linear models, support vector machines and many others. In preliminary numerical tests on structural SVM and graph-guided fused LASSO, our algorithms outperform other competing algorithms in both iteration cost and total number of data passes.
This page was built for publication: Semi-Stochastic Frank-Wolfe Algorithms with Away-Steps for Block-Coordinate Structure Problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6270109)
