Central Limit Theorems for Stochastic Optimization Algorithms Using Infinitesimal Perturbation Analysis

@article{Tang2000CentralLT,
  title={Central Limit Theorems for Stochastic Optimization Algorithms Using Infinitesimal Perturbation Analysis},
  author={Qian-Yu Tang and Han-Fu Chen},
  journal={Discrete Event Dynamic Systems},
  year={2000},
  volume={10},
  pages={5-32}
}
Central limit theorems are obtained for the \perturbation analysis Robbins-Monro single run" (PARMSR) optimization algorithm, with updates either after every L customers or after every busy period, in the context of the optimization of a GI=GI=1 queue. The PARMSR algorithm is a stochastic approximation (SA) method for the optimization of innnite-horizon… CONTINUE READING