Sökning: id:"swepub:oai:DiVA.org:kth-16063" >
Bayesian model lear...
Bayesian model learning based on a parallel MCMC strategy
-
- Corander, Jukka (författare)
- Institutionen för matematik och statistik Helsingfors universitet
-
- Gyllenberg, Mats (författare)
- Insitution för matematik och statistik Helsingfors universitet
-
- Koski, Timo (författare)
- Linköpings universitet,Tekniska högskolan,Matematisk statistik
-
(creator_code:org_t)
- Springer Science and Business Media LLC, 2006
- 2006
- Engelska.
-
Ingår i: Statistics and computing. - : Springer Science and Business Media LLC. - 0960-3174 .- 1573-1375. ; 16:4, s. 355-362
- Relaterad länk:
-
http://springerlink....
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- We introduce a novel Markov chain Monte Carlo algorithm for estimation of posterior probabilities over discrete model spaces. Our learning approach is applicable to families of models for which the marginal likelihood can be analytically calculated, either exactly or approximately, given any fixed structure. It is argued that for certain model neighborhood structures, the ordinary reversible Metropolis-Hastings algorithm does not yield an appropriate solution to the estimation problem. Therefore, we develop an alternative, non-reversible algorithm which can avoid the scaling effect of the neighborhood. To efficiently explore a model space, a finite number of interacting parallel stochastic processes is utilized. Our interaction scheme enables exploration of several local neighborhoods of a model space simultaneously, while it prevents the absorption of any particular process to a relatively inferior state. We illustrate the advantages of our method by an application to a classification model. In particular, we use an extensive bacterial database and compare our results with results obtained by different methods for the same data.
Ämnesord
- NATURVETENSKAP -- Matematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics (hsv//eng)
Nyckelord
- Bayesian analysis
- Markov chain Monte Carlo
- model learning
- parallel
- search
- chain monte-carlo
- markov-chains
- stochastic complexity
- enterobacteriaceae
- identification
- classification
- distributions
- inference
- algorithm
- MATHEMATICS
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas