Sökning: id:"swepub:oai:DiVA.org:uu-145343" >
Limit theorems for ...
Limit theorems for stochastic approximation algorithms.
-
- Renlund, Henrik, 1979- (författare)
- Uppsala universitet,Matematisk statistik
-
(creator_code:org_t)
- 2011
- Engelska 26 s.
-
Serie: U.U.D.M ; 2011:6
- Relaterad länk:
-
https://urn.kb.se/re...
Abstract
Ämnesord
Stäng
- We prove a central limit theorem applicable to one dimensional stochastic approximation algorithms that converge to a point where the error terms of the algorithm do not vanish. We show how this applies to a certain class of these algorithms that in particular covers a generalized Pólya urn model, which is also discussed. In addition, we show how to scale these algorithms in some cases where we cannot determine the limiting distribution but expect it to be non-normal.
Ämnesord
- NATURVETENSKAP -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Probability Theory and Statistics (hsv//eng)
Nyckelord
- stochastic approximation algorithms
- central limit theorem
- generalized Polya urn
- Mathematical statistics
- Matematisk statistik
- Mathematical Statistics
- Matematisk statistik
Publikations- och innehållstyp
- vet (ämneskategori)
- rap (ämneskategori)