Improved SVRG for finite sum structure optimization with application to binary classification
Guangmei Shao, Wei Xue, Gaohang Yu, Xiao Fen Zheng · Journal of Industrial and Management Optimization · 2019
This paper looks at a stochastic variance reduced gradient (SVRG) method for minimizing the sum of a finite number of smooth convex functions, which has been involved widely in the field of machine learning and data mining. Inspired by the excellent performance of two-point stepsize gradient method in batch learning, in this paper we present an improved SVRG algorithm, named stochastic two-point stepsize gradient method. Under some mild conditions, the proposed method achieves a linear convergence rate $ O(\rho^k) $ for smooth and strongly convex functions, where $ \rho\in(0.68, 1) $. Simulation experiments on several benchmark data sets are reported to demonstrate the performance of the proposed method.