Randomized Difference Two-Timescale Simultaneous Perturbation Stochastic Approximation Algorithms for Simulation Optimization of Hidden Markov Models

Abstract

We propose two finite difference two-timescale simultaneous perturbation stochastic approximation (SPSA) algorithms for simulation optimization of hidden Markov models. Stability and convergence of both the algorithms is proved. Numerical experiments on a queueing model with high dimensional parameter vectors demonstrate orders of magnitude faster convergence using these algorithms over related (N + 1)-Simulation finite difference analogues and another Two-Simulation finite difference algorithm that updates in cycles.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2000
Accession Number
ADA637176

Entities

People

  • Michael C. Fu
  • Shalabh Bhatnagar
  • Shashank Bhatnagar
  • Steven I Marcus

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Analogs
  • Computational Science
  • Convergence
  • Differential Equations
  • Engineering
  • Equations
  • Hidden Markov Models
  • Markov Models
  • Models
  • Network Protocols
  • Optimization
  • Perturbations
  • Probabilistic Models
  • Probability
  • Random Variables
  • Simulations

Readers

  • Control Systems Engineering.
  • Mathematical Modeling and Probability Theory.
  • Operations Research