Limitations of polynomial chaos expansions in the Bayesian solution of inverse problems
Journal Article
·
· Journal of Computational Physics
- Lawrence Berkeley National Laboratory (United States)
- Department of Mathematics, University of Kansas (United States)
Polynomial chaos expansions are used to reduce the computational cost in the Bayesian solutions of inverse problems by creating a surrogate posterior that can be evaluated inexpensively. We show, by analysis and example, that when the data contain significant information beyond what is assumed in the prior, the surrogate posterior can be very different from the posterior, and the resulting estimates become inaccurate. One can improve the accuracy by adaptively increasing the order of the polynomial chaos, but the cost may increase too fast for this to be cost effective compared to Monte Carlo sampling without a surrogate posterior.
- OSTI ID:
- 22382181
- Journal Information:
- Journal of Computational Physics, Journal Name: Journal of Computational Physics Vol. 282; ISSN JCTPAH; ISSN 0021-9991
- Country of Publication:
- United States
- Language:
- English
Traveling-Standing Water Waves and Microseisms
|
text | January 2013 |
| Implicit particle filters for data assimilation | preprint | January 2010 |
| Uncertainty quantification and weak approximation of an elliptic inverse problem | preprint | January 2011 |
Magnetometric resistivity tomography using chaos polynomial expansion
|
journal | February 2020 |
Joint state-parameter estimation of a nonlinear stochastic energy balance model from sparse noisy data
|
posted_content | April 2019 |
| Joint state-parameter estimation of a nonlinear stochastic energy balance model from sparse noisy data | text | January 2019 |
Joint state-parameter estimation of a nonlinear stochastic energy balance model from sparse noisy data
|
journal | January 2019 |
Similar Records
Limitations of polynomial chaos expansions in the Bayesian solution of inverse problems
Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
Stochastic spectral methods for efficient Bayesian solution of inverse problems.
Journal Article
·
Mon Nov 17 23:00:00 EST 2014
· Journal of Computational Physics
·
OSTI ID:1524015
Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
Journal Article
·
Wed Apr 01 00:00:00 EDT 2009
· Journal of Computational Physics
·
OSTI ID:21167764
Stochastic spectral methods for efficient Bayesian solution of inverse problems.
Journal Article
·
Mon Aug 01 00:00:00 EDT 2005
· Proposed for publication in the American Institute of Physics.
·
OSTI ID:971800