Buchumschlag

Deep importance sampling using tensor trains with application to a priori and a posteriori rare events

Constraints are a natural choice for prior information in Bayesian inference. In various applications, the parameters of interest lie on the boundary of the constraint set. In this paper, we use a method that implicitly defines a constrained prior such that the posterior assigns positive probability...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cui, Tiangang (VerfasserIn) , Dolgov, Sergey (VerfasserIn) , Scheichl, Robert (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: Feb 2024
In: SIAM journal on scientific computing
Year: 2024, Jahrgang: 46, Heft: 1, Pages: C1-C29
ISSN:1095-7197
DOI:10.1137/23M1546981
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1137/23M1546981
Verlag, lizenzpflichtig, Volltext: https://epubs.siam.org/doi/10.1137/23M1546981
Volltext
Verfasserangaben:Tiangang Cui, Sergey Dolgov, Robert Scheichl

MARC

LEADER 00000caa a2200000 c 4500
001 1913791440
003 DE-627
005 20250716221128.0
007 cr uuu---uuuuu
008 250108s2024 xx |||||o 00| ||eng c
024 7 |a 10.1137/23M1546981  |2 doi 
035 |a (DE-627)1913791440 
035 |a (DE-599)KXP1913791440 
035 |a (OCoLC)1528015638 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 27  |2 sdnb 
100 1 |a Cui, Tiangang  |e VerfasserIn  |0 (DE-588)1333250436  |0 (DE-627)1891362518  |4 aut 
245 1 0 |a Deep importance sampling using tensor trains with application to a priori and a posteriori rare events  |c Tiangang Cui, Sergey Dolgov, Robert Scheichl 
264 1 |c Feb 2024 
300 |a 29 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 08.01.2025 
520 |a Constraints are a natural choice for prior information in Bayesian inference. In various applications, the parameters of interest lie on the boundary of the constraint set. In this paper, we use a method that implicitly defines a constrained prior such that the posterior assigns positive probability to the boundary of the constraint set. We show that by projecting posterior mass onto a polyhedral constraint set, we obtain a new posterior with a rich probabilistic structure on the boundary of that set. If the original posterior is a Gaussian, then such a projection can be done efficiently. We apply the method to Bayesian linear inverse problems, in which case samples can be obtained by repeatedly solving constrained least squares problems, similar to an MAP estimate but with perturbations in the data. When combined into a Bayesian hierarchical model and the constraint set is a polyhedral cone, we can derive a Gibbs sampler to efficiently sample from the hierarchical model. To show the effect of projecting the posterior, we applied the method to deblurring and CT examples. 
700 1 |a Dolgov, Sergey  |d 1988-  |e VerfasserIn  |0 (DE-588)1056973234  |0 (DE-627)794331092  |0 (DE-576)412951290  |4 aut 
700 1 |a Scheichl, Robert  |d 1972-  |e VerfasserIn  |0 (DE-588)1173753842  |0 (DE-627)1043602305  |0 (DE-576)515668532  |4 aut 
773 0 8 |i Enthalten in  |a Society for Industrial and Applied Mathematics  |t SIAM journal on scientific computing  |d Philadelphia, Pa. : SIAM, 1993  |g 46(2024), 1 vom: Feb., Seite C1-C29  |h Online-Ressource  |w (DE-627)266885292  |w (DE-600)1468391-X  |w (DE-576)078589967  |x 1095-7197  |7 nnas 
773 1 8 |g volume:46  |g year:2024  |g number:1  |g month:02  |g pages:C1-C29  |g extent:29  |a Deep importance sampling using tensor trains with application to a priori and a posteriori rare events 
856 4 0 |u https://doi.org/10.1137/23M1546981  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://epubs.siam.org/doi/10.1137/23M1546981  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20250108 
993 |a Article 
994 |a 2024 
998 |g 1173753842  |a Scheichl, Robert  |m 1173753842:Scheichl, Robert  |d 110000  |d 110400  |e 110000PS1173753842  |e 110400PS1173753842  |k 0/110000/  |k 1/110000/110400/  |p 3  |y j 
999 |a KXP-PPN1913791440  |e 4646826526 
BIB |a Y 
SER |a journal 
JSO |a {"relHost":[{"part":{"extent":"29","volume":"46","year":"2024","issue":"1","pages":"C1-C29","text":"46(2024), 1 vom: Feb., Seite C1-C29"},"corporate":[{"display":"Society for Industrial and Applied Mathematics","role":"aut"}],"title":[{"title_sort":"SIAM journal on scientific computing","title":"SIAM journal on scientific computing"}],"language":["eng"],"disp":"Society for Industrial and Applied MathematicsSIAM journal on scientific computing","titleAlt":[{"title":"Journal on scientific and statistical computing"},{"title":"Journal on scientific computing"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"origin":[{"dateIssuedKey":"1993","publisherPlace":"Philadelphia, Pa.","dateIssuedDisp":"1993-","publisher":"SIAM"}],"note":["Gesehen am 02.07.2021"],"physDesc":[{"extent":"Online-Ressource"}],"recId":"266885292","name":{"displayForm":["Society for Industrial and Applied Mathematics"]},"pubHistory":["14.1993 -"],"id":{"eki":["266885292"],"issn":["1095-7197"],"zdb":["1468391-X"]}}],"person":[{"role":"aut","display":"Cui, Tiangang","given":"Tiangang","family":"Cui"},{"role":"aut","display":"Dolgov, Sergey","family":"Dolgov","given":"Sergey"},{"given":"Robert","family":"Scheichl","display":"Scheichl, Robert","role":"aut"}],"title":[{"title_sort":"Deep importance sampling using tensor trains with application to a priori and a posteriori rare events","title":"Deep importance sampling using tensor trains with application to a priori and a posteriori rare events"}],"physDesc":[{"extent":"29 S."}],"note":["Gesehen am 08.01.2025"],"origin":[{"dateIssuedDisp":"Feb 2024","dateIssuedKey":"2024"}],"id":{"doi":["10.1137/23M1546981"],"eki":["1913791440"]},"recId":"1913791440","language":["eng"],"name":{"displayForm":["Tiangang Cui, Sergey Dolgov, Robert Scheichl"]},"type":{"media":"Online-Ressource","bibl":"article-journal"}} 
SRT |a CUITIANGANDEEPIMPORT2024 

Ähnliche Einträge