Stochastic Gradient Estimation
Abstract
The author considers the problem of efficiently estimating gradients from stochastic simulation. Although the primary motivation is their use in simulation optimization, the resulting estimators also can be useful in other ways, such as in sensitivity analysis. The main approaches described are finite differences (including simultaneous perturbations), perturbation analysis, the likelihood ratio/score function method, and the use of weak derivatives. Three examples of simulation optimization are presented. These examples are a stochastic activity network, a single-server queue, and an inventory control system.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2005
- Accession Number
- ADA438511
Entities
People
- Michael C. Fu
Organizations
- University of Maryland