A modified second‐order SPSA optimization algorithm for finite samples

DOI10.1002/ACS.715MaRDI QIDQ4545955zbMATH OpenOpenAlexFDO

Authors Xun Zhu, James C. Spall

Publication date 18 August 2002

Published in International Journal of Adaptive Control and Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/acs.715

Mathematics Subject Classification ID

Perturbations in control/observation systems (93C73)

Recommendations

• Nonlinear conjugate gradient method based SPSA
• A simultaneous perturbation stochastic approximation algorithm based on quasi-Newton method
• 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

Cites work

• Adaptive stochastic approximation by the simultaneous perturbation method
• Matrix Analysis
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• On Asymptotic Normality in Stochastic Approximation

Cited in

(5)

• Simultaneous perturbation Newton algorithms for simulation optimization
• Nonlinear conjugate gradient method based SPSA
• Application of stochastic approximation techniques in neural modelling and control
• Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization
• Simultaneous perturbation stochastic approximation: towards one-measurement per iteration

This page was built for publication: A modified second‐order SPSA optimization algorithm for finite samples

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4545955)