Skip to main content

Advertisement

SpringerLink
Log in
Menu
Find a journal Publish with us
Search
Cart
  1. Home
  2. Probability Theory and Related Fields
  3. Article
Asymptotic behavior of constrained stochastic approximations via the theory of large deviations
Download PDF
Download PDF
  • Published: 01 June 1987

Asymptotic behavior of constrained stochastic approximations via the theory of large deviations

  • Paul Dupuis1 &
  • Harold J. Kushner1 

Probability Theory and Related Fields volume 75, pages 223–244 (1987)Cite this article

  • 179 Accesses

  • 19 Citations

  • Metrics details

Summary

Let G be a bounded convex set, and Π G the projection onto G, and \(\{ \xi _j \} \) a bounded random process. Projected algorithms of the types \(X_{n + 1}^\varepsilon = \Pi _G (X_n^\varepsilon + \varepsilon b(X_n^\varepsilon ,\xi _n ))({\text{or }}X_{n + 1} = \Pi _G (X_n + a_n b(X_n ,\xi _n ))\), where 0<a n→0, Σ a n =∞) occur frequently in applications (among other places) in control and communications theory. The asymptotic convergence properties of {X ε n } as ε→0, εn→∞, have been well analyzed in the literature. Here, we use large deviations methods to get a more thorough understanding of the global behavior. Let Θ be a stable point of the algorithm in the sense that X ε n →Θ in distribution as ε→0, nε→∞. For the unconstrained case, rate of convergence results involve showing asymptotic normality of \(\{ (X_n^\varepsilon - {{\Theta )} \mathord{\left/ {\vphantom {{\Theta )} {\sqrt \varepsilon }}} \right. \kern-\nulldelimiterspace} {\sqrt \varepsilon }}\} \), and use linearizations about Θ. In the constrained case Θ is often on ∂G, and such methods are inapplicable. But the large deviations method yields an alternative which is often more useful in the applications. The action functionals are derived and their properties (lower semicontinuity, etc.) are obtained. The statistics (mean value, etc.) of the escape times from a neighborhood of Θ are obtained, and the global behavior on the infinite interval is described.

Download to read the full article text

Working on a manuscript?

Avoid the common mistakes

References

  1. Kushner, H.J., Clark, D.S.: Stochastic approximation methods for constrained and unconstrained systems. Berlin Heidelberg New York: Springer 1978

    Book  MATH  Google Scholar 

  2. Kushner, H.J., Shwartz, A.: An invariant measure approach to the convergence of stochastic approximations with state-dependent noise. SIAM J. on Control and Optim. 22, 13–27 (1984)

    Article  MathSciNet  MATH  Google Scholar 

  3. Ermoliov, Yu.: Methods of stochastic programming (in Russian). Moscow: Nauka 1976

    Google Scholar 

  4. Kushner, H.J., Schwarz, A.: Stochastic approximation in Hilbert space: Identification and optimization of linear continuous parameter systems. To appear in SIAM J. on Control and Optimization

  5. Pflug, G.: Stochastic minimization with constant step-sizes. To appear in SIAM J. on Control and Optimization

  6. Freidlin, M.I.: The averaging principle and theorems on large deviations. Russian Math. Surveys, 33, 117–176 (1978)

    Article  MathSciNet  Google Scholar 

  7. Kushner, H.J.: Robustness and approximation of escape times and large deviations estimates for systems with small noise effects. SIAM J. Appl. Math. 44, 160–182 (1984)

    Article  MathSciNet  MATH  Google Scholar 

  8. Dupuis, P., Kushner, H.J.: Stochastic approximation via large deviations: Asymptotic properties. To appear in SIAM J. on Control and Optimization September 1985

  9. Varadhan, S.R.S.: Large deviations and applications. CBMS-NSF Regional Conference Series, SIAM, Philadelphia 1984

    Book  MATH  Google Scholar 

  10. Freidlin, M.I., Ventsell, A.D.: Random perturbations of dynamical systems. Berlin Heidelberg New York: Springer 1984

    Book  Google Scholar 

  11. Parthasarathy, T.: Selection theorems and their applications. Lect. Notes Math. 263. Berlin Heidelberg New York: Springer 1972

    MATH  Google Scholar 

  12. Kushner, H.J.: Approximation and weak convergence methods for random processes; with applications to stochastic systems theory. MIT Press, Cambridge, Mass. 1984

    MATH  Google Scholar 

  13. Korostelev, A.P.: Stochastic recurrent processes. Moscow: Nauka 1984

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Lefschetz Center for Dynamical Systems, Division of Applied Mathematics, Brown University, 02912, Providence, RI, USA

    Paul Dupuis & Harold J. Kushner

Authors
  1. Paul Dupuis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Harold J. Kushner
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Research has been supported in part by the US Army Research Office under Contract #DAAG 29-84-K-0082, and in part by the Office of Naval Research under Contract #N00014-83-K0542

Research has been supported in part by the National Science Foundation Grant #ECS 82-11476, and the Air Force Office of Scientific Research under Contract #AF-AFOSR 81-0116

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Dupuis, P., Kushner, H.J. Asymptotic behavior of constrained stochastic approximations via the theory of large deviations. Probab. Th. Rel. Fields 75, 223–244 (1987). https://doi.org/10.1007/BF00354035

Download citation

  • Received: 10 August 1985

  • Revised: 10 January 1987

  • Published: 01 June 1987

  • Issue Date: June 1987

  • DOI: https://doi.org/10.1007/BF00354035

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Keywords

  • Asymptotic Behavior
  • Statistical Theory
  • Random Process
  • Action Functional
  • Convergence Property
Download PDF

Working on a manuscript?

Avoid the common mistakes

Advertisement

Search

Navigation

  • Find a journal
  • Publish with us

Discover content

  • Journals A-Z
  • Books A-Z

Publish with us

  • Publish your research
  • Open access publishing

Products and services

  • Our products
  • Librarians
  • Societies
  • Partners and advertisers

Our imprints

  • Springer
  • Nature Portfolio
  • BMC
  • Palgrave Macmillan
  • Apress
  • Your US state privacy rights
  • Accessibility statement
  • Terms and conditions
  • Privacy policy
  • Help and support

167.114.118.210

Not affiliated

Springer Nature

© 2023 Springer Nature