A Linearly-Convergent Stochastic L-BFGS Algorithm
From MaRDI portal
Publication:6264375
arXiv1508.02087MaRDI QIDQ6264375
Author name not available (Why is that?)
Publication date: 9 August 2015
Abstract: We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic variant of L-BFGS proposed in Byrd et al. (2014) as well as a recent approach to variance reduction for stochastic gradient descent from Johnson and Zhang (2013). We demonstrate experimentally that our algorithm performs well on large-scale convex and non-convex optimization problems, exhibiting linear convergence and rapidly solving the optimization problems to high levels of precision. Furthermore, we show that our algorithm performs well for a wide-range of step sizes, often differing by several orders of magnitude.
Has companion code repository: https://github.com/crastogi/sLBFGS
This page was built for publication: A Linearly-Convergent Stochastic L-BFGS Algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6264375)
