[Ml-stat-talks] IDeAS seminar: Tong Zhang (Rutgers) Thursday @ 3:45 pm
rigollet at Princeton.EDU
Tue Feb 26 15:34:51 EST 2013
Date: February 28
Room: 102A McDonnell Hall - 3:45 pm (special time) IDeAS Seminar
Speaker: Tong Zhang, Rutgers University
Title: Stochastic Dual Coordinate Ascent and its Proximal Extension for Regularized Loss Minimization
Abstract: Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closely related Dual Coordinate Ascent (DCA) method has been implemented in various software packages, it has so far lacked good convergence analysis. We present a new analysis of Stochastic Dual Coordinate Ascent (SDCA) showing that this class of methods enjoy strong theoretical guarantees that are comparable or better than SGD. This analysis justifies the effectiveness of SDCA for practical applications. Moreover, we introduce a proximal version of dual coordinate ascent method. We demonstrate how the derived algorithmic framework can be used for numerous regularized loss minimization problems, including L1 regularization and structured output SVM. The convergence rates we obtain match or improve state-of-the-art results.
Joint work with Shai Shalev-Shwartz
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks