A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2004; you can also visit the original URL.
The file type is application/pdf
.
Matrix conditioning and adaptive simultaneous perturbation stochastic approximation method
2001
Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148)
This paper proposes a modification to the simultaneous perturbation stochastic approximation (SPSA) methods based on the comparisons made between the first order and the second order SPSA (1SPSA and 2SPSA) algorithms from the perspective of loss function Hessian. At finite iterations, the convergence rate depends on the matrix conditioning of the loss function Hessian. It is shown that 2SPSA converges more slowly for a loss function with an ill-conditioned Hessian than the one with a
doi:10.1109/acc.2001.945918
fatcat:fl3gzjj6qjeb3l7b2fw4svubzu