IDEAS home Printed from https://ideas.repec.org/a/eee/spapps/v125y2015i5p1715-1755.html
   My bibliography  Save this article

Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema

Author

Listed:
  • Tadić, Vladislav B.

Abstract

The asymptotic behavior of stochastic gradient algorithms is studied. Relying on results from differential geometry (the Lojasiewicz gradient inequality), the single limit-point convergence of the algorithm iterates is demonstrated and relatively tight bounds on the convergence rate are derived. In sharp contrast to the existing asymptotic results, the new results presented here allow the objective function to have multiple and non-isolated minima. The new results also offer new insights into the asymptotic properties of several classes of recursive algorithms which are routinely used in engineering, statistics, machine learning and operations research.

Suggested Citation

  • Tadić, Vladislav B., 2015. "Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema," Stochastic Processes and their Applications, Elsevier, vol. 125(5), pages 1715-1755.
    • Handle: RePEc:eee:spapps:v:125:y:2015:i:5:p:1715-1755
    DOI: 10.1016/j.spa.2014.11.001
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0304414914002671
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.spa.2014.11.001?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Borkar,Vivek S., 2008. "Stochastic Approximation," Cambridge Books, Cambridge University Press, number 9780521515924.
    2. Ming Gao Gu & Hong‐Tu Zhu, 2001. "Maximum likelihood estimation for spatial models by Markov chain Monte Carlo stochastic approximation," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 63(2), pages 339-355.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Prasenjit Karmakar & Shalabh Bhatnagar, 2018. "Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning," Mathematics of Operations Research, INFORMS, vol. 43(1), pages 130-151, February.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li Cai, 2010. "High-dimensional Exploratory Item Factor Analysis by A Metropolis–Hastings Robbins–Monro Algorithm," Psychometrika, Springer;The Psychometric Society, vol. 75(1), pages 33-57, March.
    2. L. Sun & M. K. Clayton, 2008. "Bayesian Analysis of Crossclassified Spatial Data with Autocorrelation," Biometrics, The International Biometric Society, vol. 64(1), pages 74-84, March.
    3. Panos Toulis & Thibaut Horel & Edoardo M. Airoldi, 2021. "The proximal Robbins–Monro method," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 83(1), pages 188-212, February.
    4. Koutchade, Philippe & Carpentier, Alain & Féménia, Fabienne, 2015. "Empirical modeling of production decisions of heterogeneous farmers with random parameter models," Working Papers 210097, Institut National de la recherche Agronomique (INRA), Departement Sciences Sociales, Agriculture et Alimentation, Espace et Environnement (SAE2).
    5. Matthias von Davier & Sandip Sinharay, 2010. "Stochastic Approximation Methods for Latent Regression Item Response Models," Journal of Educational and Behavioral Statistics, , vol. 35(2), pages 174-193, April.
    6. Qian, Zhiguang & Shapiro, Alexander, 2006. "Simulation-based approach to estimation of latent variable models," Computational Statistics & Data Analysis, Elsevier, vol. 51(2), pages 1243-1259, November.
    7. Helin Zhu & Joshua Hale & Enlu Zhou, 2018. "Simulation optimization of risk measures with adaptive risk levels," Journal of Global Optimization, Springer, vol. 70(4), pages 783-809, April.
    8. Koutchadé, Philippe & Carpentier, Alain & Féménia, Fabienne, 2015. "Empirical modelling of production decisions of heterogeneous farmers with mixed models," 2015 AAEA & WAEA Joint Annual Meeting, July 26-28, San Francisco, California 205098, Agricultural and Applied Economics Association.
    9. Koutchade, Philippe & Carpentier, Alain & Femenia, Fabienne, 2015. "Accounting for unobserved heterogeneity in micro-econometric agricultural production models: a random parameter approach," 2015 Conference, August 9-14, 2015, Milan, Italy 212015, International Association of Agricultural Economists.
    10. Wanchuang Zhu & Yanan Fan, 2023. "A synthetic likelihood approach for intractable markov random fields," Computational Statistics, Springer, vol. 38(2), pages 749-777, June.
    11. Lee, Sik-Yum & Xu, Liang, 2004. "Influence analyses of nonlinear mixed-effects models," Computational Statistics & Data Analysis, Elsevier, vol. 45(2), pages 321-341, March.
    12. Georgios Chasparis & Jeff Shamma, 2012. "Distributed Dynamic Reinforcement of Efficient Outcomes in Multiagent Coordination and Network Formation," Dynamic Games and Applications, Springer, vol. 2(1), pages 18-50, March.
    13. R. Reeves, 2004. "Efficient recursions for general factorisable models," Biometrika, Biometrika Trust, vol. 91(3), pages 751-757, September.
    14. Jin, Ick Hoon & Liang, Faming, 2014. "Use of SAMC for Bayesian analysis of statistical models with intractable normalizing constants," Computational Statistics & Data Analysis, Elsevier, vol. 71(C), pages 402-416.
    15. Bee, Marco & Espa, Giuseppe & Giuliani, Diego, 2015. "Approximate maximum likelihood estimation of the autologistic model," Computational Statistics & Data Analysis, Elsevier, vol. 84(C), pages 14-26.
    16. Moon, Sangkil & Azizi, Kathryn, 2013. "Finding Donors by Relationship Fundraising," Journal of Interactive Marketing, Elsevier, vol. 27(2), pages 112-129.
    17. Chopin, Nicolas & Gadat, Sébastien & Guedj, Benjamin & Guyader, Arnaud & Vernet, Elodie, 2015. "On some recent advances in high dimensional Bayesian Statistics," TSE Working Papers 15-557, Toulouse School of Economics (TSE).
    18. Yao Chen & Qingyi Gao & Xiao Wang, 2022. "Inferential Wasserstein generative adversarial networks," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 84(1), pages 83-113, February.
    19. Sy-Miin Chow & Zhaohua Lu & Andrew Sherwood & Hongtu Zhu, 2016. "Fitting Nonlinear Ordinary Differential Equation Models with Random Effects and Unknown Initial Conditions Using the Stochastic Approximation Expectation–Maximization (SAEM) Algorithm," Psychometrika, Springer;The Psychometric Society, vol. 81(1), pages 102-134, March.
    20. Gu, Minggao & Wu, Yueqin & Huang, Bin, 2014. "Partial marginal likelihood estimation for general transformation models," Journal of Multivariate Analysis, Elsevier, vol. 123(C), pages 1-18.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:spapps:v:125:y:2015:i:5:p:1715-1755. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/505572/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.