Stochastic Conjugate Gradient Algorithm With Variance Reduction.
other · Level V
Where this comes from
- Record sourced from PubMed, PMID 30281486.
- Also identified by DOI 10.1109/TNNLS.2018.2868835.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
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<sup>1</sup> 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.<sup>1</sup>CGVR algorithm is available on github: https://github.com/xbjin/cgvr.