Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals. / Mosegaard, K.

81st EAGE Conference and Exhibition 2019 Workshop Programme. EAGE Publishing BV, 2019. (81st EAGE Conference and Exhibition 2019 Workshop Programme).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Mosegaard, K 2019, Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals. in 81st EAGE Conference and Exhibition 2019 Workshop Programme. EAGE Publishing BV, 81st EAGE Conference and Exhibition 2019 Workshop Programme, 81st EAGE Conference and Exhibition 2019 Workshop Programme, London, United Kingdom, 03/06/2019. https://doi.org/10.3997/2214-4609.201901991

APA

Mosegaard, K. (2019). Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals. In 81st EAGE Conference and Exhibition 2019 Workshop Programme EAGE Publishing BV. 81st EAGE Conference and Exhibition 2019 Workshop Programme https://doi.org/10.3997/2214-4609.201901991

Vancouver

Mosegaard K. Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals. In 81st EAGE Conference and Exhibition 2019 Workshop Programme. EAGE Publishing BV. 2019. (81st EAGE Conference and Exhibition 2019 Workshop Programme). https://doi.org/10.3997/2214-4609.201901991

Author

Mosegaard, K. / Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals. 81st EAGE Conference and Exhibition 2019 Workshop Programme. EAGE Publishing BV, 2019. (81st EAGE Conference and Exhibition 2019 Workshop Programme).

Bibtex

@inproceedings{be61e782904c4b2085d401fd657bbca5,
title = "Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals",
abstract = "The solution of an inverse problem is a process where an algorithm asks questions to the data. In some cases the questions are yes/no questions (accepting or rejecting a model proposed by an Markov Chain Monte Carlo (MCMC) algorithm) and in other cases the questions are more complex, as in a deterministic algorithm's quest for gradients or curvatures. However, no algorithm can ask the right question without an efficient interrogation strategy. Such a strategy comes from what we call 'prior information', either about the solution to be found, or about the nature of the forward relation. The latter strategy is particularly important and is for MCMC algorithms expressed through the 'proposal distribution'. We shall explore the importance of proposal strategies, and show that dramatic improvements can be made if information-rich strategies are employed.",
author = "K. Mosegaard",
year = "2019",
doi = "10.3997/2214-4609.201901991",
language = "English",
series = "81st EAGE Conference and Exhibition 2019 Workshop Programme",
booktitle = "81st EAGE Conference and Exhibition 2019 Workshop Programme",
publisher = "EAGE Publishing BV",
address = "Netherlands",
note = "81st EAGE Conference and Exhibition 2019 Workshop Programme ; Conference date: 03-06-2019 Through 06-06-2019",

}

RIS

TY - GEN

T1 - Efficient Monte Carlo Uncertainty Quantification through Problem-dependent Proposals

AU - Mosegaard, K.

PY - 2019

Y1 - 2019

N2 - The solution of an inverse problem is a process where an algorithm asks questions to the data. In some cases the questions are yes/no questions (accepting or rejecting a model proposed by an Markov Chain Monte Carlo (MCMC) algorithm) and in other cases the questions are more complex, as in a deterministic algorithm's quest for gradients or curvatures. However, no algorithm can ask the right question without an efficient interrogation strategy. Such a strategy comes from what we call 'prior information', either about the solution to be found, or about the nature of the forward relation. The latter strategy is particularly important and is for MCMC algorithms expressed through the 'proposal distribution'. We shall explore the importance of proposal strategies, and show that dramatic improvements can be made if information-rich strategies are employed.

AB - The solution of an inverse problem is a process where an algorithm asks questions to the data. In some cases the questions are yes/no questions (accepting or rejecting a model proposed by an Markov Chain Monte Carlo (MCMC) algorithm) and in other cases the questions are more complex, as in a deterministic algorithm's quest for gradients or curvatures. However, no algorithm can ask the right question without an efficient interrogation strategy. Such a strategy comes from what we call 'prior information', either about the solution to be found, or about the nature of the forward relation. The latter strategy is particularly important and is for MCMC algorithms expressed through the 'proposal distribution'. We shall explore the importance of proposal strategies, and show that dramatic improvements can be made if information-rich strategies are employed.

U2 - 10.3997/2214-4609.201901991

DO - 10.3997/2214-4609.201901991

M3 - Article in proceedings

AN - SCOPUS:85084020633

T3 - 81st EAGE Conference and Exhibition 2019 Workshop Programme

BT - 81st EAGE Conference and Exhibition 2019 Workshop Programme

PB - EAGE Publishing BV

T2 - 81st EAGE Conference and Exhibition 2019 Workshop Programme

Y2 - 3 June 2019 through 6 June 2019

ER -

ID: 241098353