Stability of stochastic optimization problem - nonmeasurable case
1.
SYSNO ASEP
0307732
Document Type
J - Journal Article
R&D Document Type
Journal Article
Subsidiary J
Ostatní články
Title
Stability of stochastic optimization problem - nonmeasurable case
Title
Stabilita úloh stochastické optimalizace - neměřitelný případ
Author(s)
Lachout, Petr (UTIA-B)
Source Title
Kybernetika. - : Ústav teorie informace a automatizace AV ČR, v. v. i.
- ISSN 0023-5954
Roč. 44, č. 2 (2008), s. 259-276
Number of pages
18 s.
Language
eng - English
Country
CZ - Czech Republic
Keywords
Stochastic optimization problem ; Sensitivity and stability ; Measurability ; Weak convergence of probability measures
Subject RIV
BA - General Mathematics
R&D Projects
GA201/08/0539 GA ČR - Czech Science Foundation (CSF)
Next source
Other public resources
CEZ
AV0Z10750506 - UTIA-B (2005-2011)
Annotation
This 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.