Number of the records: 1  

Stability of stochastic optimization problem - nonmeasurable case

  1. 1.
    SYSNO ASEP0307732
    Document TypeJ - Journal Article
    R&D Document TypeJournal Article
    Subsidiary JOstatní články
    TitleStability of stochastic optimization problem - nonmeasurable case
    TitleStabilita úloh stochastické optimalizace - neměřitelný případ
    Author(s) Lachout, Petr (UTIA-B)
    Source TitleKybernetika. - : Ústav teorie informace a automatizace AV ČR, v. v. i. - ISSN 0023-5954
    Roč. 44, č. 2 (2008), s. 259-276
    Number of pages18 s.
    Languageeng - English
    CountryCZ - Czech Republic
    KeywordsStochastic optimization problem ; Sensitivity and stability ; Measurability ; Weak convergence of probability measures
    Subject RIVBA - General Mathematics
    R&D ProjectsGA201/08/0539 GA ČR - Czech Science Foundation (CSF)
    Next sourceOther public resources
    CEZAV0Z10750506 - UTIA-B (2005-2011)
    AnnotationThis paper deals with stability of stochastic optimization problems in a general setting. Objective function is defined on a metric space and depends on a probability measure which is unknown, but, estimated from empirical observations. We derive stability results without precise knowledge of problem structure and without measurability assumption. The setup is illustrated on consistency of a $/varepsilon$-$M$-estimator in linear regression model.
    WorkplaceInstitute of Information Theory and Automation
    ContactMarkéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
    Year of Publishing2008
Number of the records: 1  

  This site uses cookies to make them easier to browse. Learn more about how we use cookies.