Decentralized Quasi-Newton Methods
From MaRDI portal
Abstract: We introduce the decentralized Broyden-Fletcher-Goldfarb-Shanno (D-BFGS) method as a variation of the BFGS quasi-Newton method for solving decentralized optimization problems. The D-BFGS method is of interest in problems that are not well conditioned, making first order decentralized methods ineffective, and in which second order information is not readily available, making second order decentralized methods impossible. D-BFGS is a fully distributed algorithm in which nodes approximate curvature information of themselves and their neighbors through the satisfaction of a secant condition. We additionally provide a formulation of the algorithm in asynchronous settings. Convergence of D-BFGS is established formally in both the synchronous and asynchronous settings and strong performance advantages relative to first order methods are shown numerically.
Cited in
(8)- Distributed adaptive Newton methods with global superlinear convergence
- Learning Coefficient Heterogeneity over Networks: A Distributed Spanning-Tree-Based Fused-Lasso Regression
- Hierarchical distributed optimization of constraint-coupled convex and mixed-integer programs using approximations of the dual function
- Distributed adaptive greedy quasi-Newton methods with explicit non-asymptotic convergence bounds
- Asynchronous ADMM for nonlinear continuous-time systems
- A selective review on statistical methods for massive data computation: distributed computing, subsampling, and minibatch techniques
- An inertial Bregman proximal gradient algorithm for nonconvex composite optimization problems
- Forgetting-factor regrets for distributed second-order online optimisation
This page was built for publication: Decentralized Quasi-Newton Methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620791)
