Title :
Stochastic approximation for function minimization under quantization error
Author :
Gerencsér, László ; Vágó, Zsuzsanna
Author_Institution :
Comput. & Autom. Inst., Hungarian Acad. of Sci., Budapest, Hungary
Abstract :
The simultaneous perturbation stochastic approximation (SPSA) method developed by Spall (1992) is applied and analyzed for function minimization under quantization error. It is proved that under certain conditions the estimator sequence converges with rate O(n-β/2 ) for some β>0, where the rate is measured by the Lq -norm of the estimation error for any 1⩽q<∞. The viability of SPSA for the present problem is also demonstrated by simulation results
Keywords :
approximation theory; convergence of numerical methods; minimisation; noise; quantisation (signal); stochastic processes; Kiefer Wolfovitz method; SPSA method; convergence; minimization; noise distribution; optimisation; perturbation; quantization; stochastic approximation; Additive noise; Automation; Estimation error; Linear regression; Minimization methods; Noise measurement; Quantization; Stochastic processes; Vibration measurement; Working environment noise;
Conference_Titel :
Decision and Control, 1999. Proceedings of the 38th IEEE Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5250-5
DOI :
10.1109/CDC.1999.831279
