Convergence of simultaneous perturbation stochastic approximation for nondifferentiable optimization

@article{He2003ConvergenceOS,
  title={Convergence of simultaneous perturbation stochastic approximation for nondifferentiable optimization},
  author={Ying He and Michael C. Fu and Steven I. Marcus},
  journal={IEEE Trans. Automat. Contr.},
  year={2003},
  volume={48},
  pages={1459-1463}
}
In this note, we consider simultaneous perturbation stochastic approximation for function minimization. The standard assumption for convergence is that the function be three times differentiable, although weaker assumptions have been used for special cases. However, all work that we are aware of at least requires differentiability. In this note, we relax the differentiability requirement and prove convergence using convex analysis. 
Highly Cited
This paper has 45 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 32 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Optimization of discrete event systems via simultaneous perturbation stochastic approximation

  • M. C. Fu, S. D. Hill
  • IIE Trans., vol. 29, no. 3, pp. 233–243, Mar…
  • 1997
Highly Influential
4 Excerpts

Multivariate stochastic approximation using a simultaneous perturbation gradient approximation

  • J. C. Spall
  • IEEE Trans. Automat. Contr. , vol. 37, pp. 332…
  • 1992
Highly Influential
6 Excerpts

Nondifferentiability of steady-state function in discrete event dynamic systems

  • A. Shapiro, Y. Wardi
  • IEEE Trans. Automat. Contr. , vol. 39, pp. 1707…
  • 1994
Highly Influential
3 Excerpts

A Markov decision process model for dynamic capacity allocation

  • Y. He, M. C. Fu, S. I. Marcus
  • , 2003, submitted for publication.
  • 2003
1 Excerpt

Stochastic approximation for global random optimization

  • J. L. Maryak, D. C. Chin
  • inProc. Amer. Control Conf. , Chicago, IL, 2000…
  • 2000
2 Excerpts

Similar Papers

Loading similar papers…