A simultaneous perturbation stochastic approximation algorithm based on quasi-Newton method

DOI10.13245/J.HUST.140901zbMATH Open1324.90193MaRDI QIDQ5257697FDOQ5257697

Authors: Hua Jun Zhang, Jin Zhao, Hui Luo 

Publication date: 29 June 2015

Recommendations

• Nonlinear conjugate gradient method based SPSA
• Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation
• Adaptive stochastic approximation by the simultaneous perturbation method
• Convergence rate of moments in stochastic approximation with simultaneous perturbation gradient approximation and resetting
• Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences

zbMATH Keywords

quasi-Newton methodconvergence speedsimultaneous perturbation stochastic approximationsearch directionapproximation precision

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Methods of quasi-Newton type (90C53)

Cited In (7)

• Structural optimization using the simultaneous perturbation stochastic approximation algorithm
• Optimal design of structures using the simultaneous perturbation stochastic approximation algorithm
• Nonlinear conjugate gradient method based SPSA
• Simultaneous perturbation stochastic approximation with norm-limited update vector
• Performance analysis of the simultaneous perturbation stochastic approximation algorithm on the noisy sphere model
• A modified second‐order SPSA optimization algorithm for finite samples
• Simultaneous perturbation stochastic approximation of nonsmooth functions

This page was built for publication: A simultaneous perturbation stochastic approximation algorithm based on quasi-Newton method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5257697)