Limitations of polynomial chaos expansions in the Bayesian solution of inverse problems
From MaRDI portal
Publication:728862
DOI10.1016/J.JCP.2014.11.010zbMATH Open1351.62075arXiv1404.7188OpenAlexW2021857616MaRDI QIDQ728862FDOQ728862
Authors: Fei Lu, Matthias Morzfeld, Xuemin Tu, Alexandre J. Chorin 
Publication date: 20 December 2016
Published in: Journal of Computational Physics (Search for Journal in Brave)
Abstract: 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.
Full work available at URL: https://arxiv.org/abs/1404.7188
Recommendations
- Stochastic spectral methods for efficient Bayesian solution of inverse problems
- Adaptive construction of surrogates for 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
- Adaptive multi-fidelity polynomial chaos approach to Bayesian inference in inverse problems
Cites Work
- Gaussian processes for machine learning.
- Statistical and computational inverse problems.
- A random map implementation of implicit filters
- Monte Carlo strategies in scientific computing
- Wiener chaos expansions and numerical solutions of randomly forced equations of fluid mechanics
- Inverse problems: a Bayesian perspective
- Stochastic processes and orthogonal polynomials
- Rare event simulation of small noise diffusions
- Stochastic tools in mathematics and science
- Implicit particle filters for data assimilation
- Numerical methods for stochastic computations. A spectral method approach.
- Spectral Methods for Uncertainty Quantification
- Inverse Problem Theory and Methods for Model Parameter Estimation
- Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
- A stochastic collocation approach to Bayesian inference in inverse problems
- Title not available (Why is that?)
- Uncertainty Quantification and Polynomial Chaos Techniques in Computational Fluid Dynamics
- Gaussian fields and random flow
- Relationship between a Wiener–Hermite expansion and an energy cascade
- Stochastic spectral methods for efficient Bayesian solution of inverse problems
- Fundamental limitations of polynomial chaos for uncertainty quantification in systems with intermittent instabilities
- Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
- Title not available (Why is that?)
- Hermite spectral and pseudospectral methods for nonlinear partial differential equation in multiple dimensions
- Uncertainty quantification in MD simulations. II: Bayesian inference of force-field parameters
- Solution of inverse problems with limited forward solver evaluations: a Bayesian perspective
Cited In (16)
- Adaptive multi-fidelity polynomial chaos approach to Bayesian inference in inverse problems
- A Reduced-Order-Model Bayesian Obstacle Detection Algorithm
- Iterative importance sampling algorithms for parameter estimation
- An efficient algorithm for a class of stochastic forward and inverse Maxwell models in \(\mathbb{R}^3\)
- Markov chain generative adversarial neural networks for solving Bayesian inverse problems in physics applications
- Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
- An Adaptive Surrogate Modeling Based on Deep Neural Networks for Large-Scale Bayesian Inverse Problems
- Theory and methods for random differential equations: a survey
- Bayesian inversion using adaptive polynomial chaos kriging within subset simulation
- Sequential design of computer experiments for the solution of Bayesian inverse problems
- Bayesian Model Calibration with Interpolating Polynomials based on Adaptively Weighted Leja Nodes
- Local search methods for the solution of implicit inverse problems
- Sequential Design of Computer Experiments for the Computation of Bayesian Model Evidence
- On exact posterior distributions using H-functions
- Auto-weighted Bayesian physics-informed neural networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution
- Bayesian approach to inverse time-harmonic acoustic obstacle scattering with phaseless data generated by point source waves
This page was built for publication: Limitations of polynomial chaos expansions in the Bayesian solution of inverse problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q728862)
