Abstract: We introduce a quasi-Newton method with block updates called Block BFGS. We show that this method, performed with inexact Armijo-Wolfe line searches, converges globally and superlinearly under the same convexity assumptions as BFGS. We also show that Block BFGS is globally convergent to a stationary point when applied to non-convex functions with bounded Hessian, and discuss other modifications for non-convex minimization. Numerical experiments comparing Block BFGS, BFGS and gradient descent are presented.
Recommendations
- Properties of the block BFGS update and its application to the limited-memory block BNS method for unconstrained minimization
- A generalized limited-memory BNS method based on the block BFGS update.
- A Tool for the Analysis of Quasi-Newton Methods with Application to Unconstrained Minimization
- The global convergence of a modified BFGS method for nonconvex functions
- A modified BFGS method and its superlinear convergence in nonconvex minimization with general line search rule
Cites work
- A Characterization of Superlinear Convergence and Its Application to Quasi-Newton Methods
- A Family of Variable-Metric Methods Derived by Variational Means
- A modified BFGS method and its global convergence in nonconvex minimization
- A repository of convex quadratic programming problems
- A stochastic quasi-Newton method for large-scale optimization
- Algorithm 984: ADiGator, a toolbox for the algorithmic differentiation of mathematical functions in MATLAB using source transformation via operator overloading
- Algorithms for nonlinear constraints that use lagrangian functions
- An unconstrained optimization test functions collection
- Benchmarking optimization software with performance profiles.
- Global Convergence of a Cass of Quasi-Newton Methods on Convex Problems
- scientific article; zbMATH DE number 3529352 (Why is no real title available?)
- scientific article; zbMATH DE number 6125590 (Why is no real title available?)
- Local convergence analysis for partitioned quasi-Newton updates
- On the global convergence of the BFGS method for nonconvex unconstrained optimization problems
- On the limited memory BFGS method for large scale optimization
Cited in
(9)- On block minimal residual methods
- Block extrapolation methods with applications
- Block stochastic gradient iteration for convex and nonconvex optimization
- FETI-DP, BDDC, and block Cholesky methods
- A variational derivation of a class of BFGS-like methods
- Quasi-Newton methods: superlinear convergence without line searches for self-concordant functions
- Quasi-Newton methods for machine learning: forget the past, just sample
- An overview of stochastic quasi-Newton methods for large-scale machine learning
- Preconditioned pseudo-time continuation for parameterized inverse problems
This page was built for publication: Block BFGS methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4641646)
