Stochastic Conjugate Gradient Algorithm With Variance Reduction
IEEE transactions on neural networks and learning systems(2019)
摘要
Conjugate gradient (CG) methods are a class of important methods for solving linear equations and nonlinear optimization problems. In this paper, we propose a new stochastic CG algorithm with variance reduction(1) and we prove its linear convergence with the Fletcher and Reeves method for strongly convex and smooth functions. We experimentally demonstrate that the CG with variance reduction algorithm converges faster than its counterparts for four learning models, which may be convex, nonconvex or nonsmooth. In addition, its area under the curve performance on six large-scale data sets is comparable to that of the LIBLINEAR solver for the L2-regularized L2-loss but with a significant improvement in computational efficiency.
更多查看译文
关键词
Computational efficiency,covariance reduction,empirical risk minimization (ERM),linear convergence,stochastic conjugate gradient (CG)
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络