Skip to yearly menu bar Skip to main content


Poster

Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis

Weiran Wang · Jialei Wang · Dan Garber · Dan Garber · Nati Srebro

Area 5+6+7+8 #116

Keywords: [ Large Scale Learning and Big Data ] [ Convex Optimization ] [ Component Analysis (ICA,PCA,CCA, FLDA) ]


Abstract:

We study the stochastic optimization of canonical correlation analysis (CCA), whose objective is nonconvex and does not decouple over training samples. Although several stochastic gradient based optimization algorithms have been recently proposed to solve this problem, no global convergence guarantee was provided by any of them. Inspired by the alternating least squares/power iterations formulation of CCA, and the shift-and-invert preconditioning method for PCA, we propose two globally convergent meta-algorithms for CCA, both of which transform the original problem into sequences of least squares problems that need only be solved approximately. We instantiate the meta-algorithms with state-of-the-art SGD methods and obtain time complexities that significantly improve upon that of previous work. Experimental results demonstrate their superior performance.

Live content is unavailable. Log in and register to view live content