Stopping Stochastic Approximation

Abstract

The practical application of stochastic approximation methods require a reliable means to stop the iterative process when the estimate is close to the optimal value or when further improvement of the estimate is doubtful. Conventional ideas on stopping stochastic algorithms employ probabilistic criteria based on the asymptotic distribution of the stochastic approximation process, often with the parameters of the distribution determined by sequential estimation. Difficulties may arise when this approach is applied to small (finite) samples. We propose a different approach that uses the notion of an idealized process as a companion to the stochastic approximation. A discussion of this approach to stopping stochastic approximation is offered in the context of a simple example, including some empirical results.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2003
Accession Number
ADA515432

Entities

People

  • David W. Hutchison
  • James C. Spall

Organizations

  • Johns Hopkins University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Computations
  • Convergence
  • Data Science
  • Distribution Functions
  • Estimators
  • Information Operations
  • Information Science
  • Iterations
  • Normal Distribution
  • Physics Laboratories
  • Probability
  • Probability Distributions
  • Random Variables
  • Sequences
  • Statistical Algorithms

Fields of Study

  • Mathematics

Readers

  • Calculus or Mathematical Analysis
  • Mathematical Modeling and Probability Theory.
  • Regression Analysis.