Buchumschlag

Approximate variational inference based on a finite sample of Gaussian latent variables

Variational methods are employed in situations where exact Bayesian inference becomes intractable due to the difficulty in performing certain integrals. Typically, variational methods postulate a tractable posterior and formulate a lower bound on the desired integral to be approximated, e.g. margina...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gianniotis, Nikolaos (VerfasserIn) , Schnörr, Christoph (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: May 2016
In: Pattern analysis and applications
Year: 2016, Jahrgang: 19, Heft: 2, Pages: 475-485
ISSN:1433-755X
DOI:10.1007/s10044-015-0496-9
Online-Zugang:Resolving-System, Volltext: http://dx.doi.org/10.1007/s10044-015-0496-9
Verlag, Volltext: https://link.springer.com/article/10.1007/s10044-015-0496-9
Volltext
Verfasserangaben:Nikolaos Gianniotis, Christoph Schnörr, Christian Molkenthin, Sanjay Singh Bora

MARC

LEADER 00000caa a2200000 c 4500
001 1585753386
003 DE-627
005 20220815083857.0
007 cr uuu---uuuuu
008 181219s2016 xx |||||o 00| ||eng c
024 7 |a 10.1007/s10044-015-0496-9  |2 doi 
035 |a (DE-627)1585753386 
035 |a (DE-576)515753386 
035 |a (DE-599)BSZ515753386 
035 |a (OCoLC)1341031297 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 27  |2 sdnb 
100 1 |a Gianniotis, Nikolaos  |e VerfasserIn  |0 (DE-588)1173849874  |0 (DE-627)1043662219  |0 (DE-576)515754323  |4 aut 
245 1 0 |a Approximate variational inference based on a finite sample of Gaussian latent variables  |c Nikolaos Gianniotis, Christoph Schnörr, Christian Molkenthin, Sanjay Singh Bora 
264 1 |c May 2016 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Published online: 30 June 2015 
500 |a Gesehen am 19.12.2018 
520 |a Variational methods are employed in situations where exact Bayesian inference becomes intractable due to the difficulty in performing certain integrals. Typically, variational methods postulate a tractable posterior and formulate a lower bound on the desired integral to be approximated, e.g. marginal likelihood. The lower bound is then optimised with respect to its free parameters, the so-called variational parameters. However, this is not always possible as for certain integrals it is very challenging (or tedious) to come up with a suitable lower bound. Here, we propose a simple scheme that overcomes some of the awkward cases where the usual variational treatment becomes difficult. The scheme relies on a rewriting of the lower bound on the model log-likelihood. We demonstrate the proposed scheme on a number of synthetic and real examples, as well as on a real geophysical model for which the standard variational approaches are inapplicable. 
650 4 |a Bayesian inference 
650 4 |a Expectation maximisation 
650 4 |a Posterior estimation 
700 1 |a Schnörr, Christoph  |e VerfasserIn  |0 (DE-588)1023033348  |0 (DE-627)717351017  |0 (DE-576)168404540  |4 aut 
773 0 8 |i Enthalten in  |t Pattern analysis and applications  |d London : Springer, 1998  |g 19(2016), 2, Seite 475-485  |h Online-Ressource  |w (DE-627)301511616  |w (DE-600)1484514-3  |w (DE-576)11408825X  |x 1433-755X  |7 nnas  |a Approximate variational inference based on a finite sample of Gaussian latent variables 
773 1 8 |g volume:19  |g year:2016  |g number:2  |g pages:475-485  |g extent:11  |a Approximate variational inference based on a finite sample of Gaussian latent variables 
856 4 0 |u http://dx.doi.org/10.1007/s10044-015-0496-9  |x Resolving-System  |x Verlag  |3 Volltext 
856 4 0 |u https://link.springer.com/article/10.1007/s10044-015-0496-9  |x Verlag  |3 Volltext 
951 |a AR 
992 |a 20181219 
993 |a Article 
994 |a 2016 
998 |g 1023033348  |a Schnörr, Christoph  |m 1023033348:Schnörr, Christoph  |d 110000  |d 110200  |d 110000  |d 110400  |d 700000  |d 708000  |e 110000PS1023033348  |e 110200PS1023033348  |e 110000PS1023033348  |e 110400PS1023033348  |e 700000PS1023033348  |e 708000PS1023033348  |k 0/110000/  |k 1/110000/110200/  |k 0/110000/  |k 1/110000/110400/  |k 0/700000/  |k 1/700000/708000/  |p 2 
999 |a KXP-PPN1585753386  |e 3038785172 
BIB |a Y 
SER |a journal 
JSO |a {"recId":"1585753386","name":{"displayForm":["Nikolaos Gianniotis, Christoph Schnörr, Christian Molkenthin, Sanjay Singh Bora"]},"physDesc":[{"extent":"11 S."}],"relHost":[{"part":{"year":"2016","text":"19(2016), 2, Seite 475-485","pages":"475-485","extent":"11","volume":"19","issue":"2"},"origin":[{"publisher":"Springer","dateIssuedKey":"1998","dateIssuedDisp":"1998-","publisherPlace":"London ; Berlin [u.a.]"}],"note":["Gesehen am 28.03.06"],"titleAlt":[{"title":"PAA"}],"title":[{"title":"Pattern analysis and applications","title_sort":"Pattern analysis and applications","subtitle":"PAA"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"disp":"Approximate variational inference based on a finite sample of Gaussian latent variablesPattern analysis and applications","id":{"zdb":["1484514-3"],"issn":["1433-755X"],"eki":["301511616"]},"physDesc":[{"extent":"Online-Ressource"}],"recId":"301511616","pubHistory":["1.1998 -"]}],"id":{"eki":["1585753386"],"doi":["10.1007/s10044-015-0496-9"]},"person":[{"role":"aut","given":"Nikolaos","family":"Gianniotis","display":"Gianniotis, Nikolaos"},{"display":"Schnörr, Christoph","family":"Schnörr","given":"Christoph","role":"aut"}],"language":["eng"],"note":["Published online: 30 June 2015","Gesehen am 19.12.2018"],"origin":[{"dateIssuedKey":"2016","dateIssuedDisp":"May 2016"}],"title":[{"title":"Approximate variational inference based on a finite sample of Gaussian latent variables","title_sort":"Approximate variational inference based on a finite sample of Gaussian latent variables"}],"type":{"media":"Online-Ressource","bibl":"article-journal"}} 
SRT |a GIANNIOTISAPPROXIMAT2016 

Ähnliche Einträge