A Unified View of Infinitesimal Perturbation Analysis and Likelihood Ratios

Abstract

A view of the likelihood ratio (LR) gradient estimation technique (also called the score function (SF) method) is presented under which infinitesimal perturbation analysis (IPA) can be viewed as a (degenerate) special case, by selecting appropriately what the random component omega effectively represents. Varying the actual meaning of omega (i.e., defining the underlying sample space in different ways) might define different variants of the LR method, some of them mixing IPA with more traditional LR. We illustrate this by many examples. We also give general conditions under which the gradient estimators are unbiased.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1989
Accession Number
ADA210682

Entities

People

  • Pierre L'ecuyer

Organizations

  • Stanford University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Cost Estimates
  • Dynamic Programming
  • Estimators
  • Markov Chains
  • Markov Processes
  • Operations Research
  • Perturbations
  • Probability
  • Random Variables
  • Sampling
  • Simulations
  • Statistical Algorithms
  • Steady State
  • Theorems
  • United States
  • Universities

Fields of Study

  • Mathematics

Readers

  • Linear Algebra
  • Regression Analysis.
  • Systems Analysis and Design

Technology Areas

  • Space