Variational Bayesian Approximation of Inverse Problems using Sparse Precision Matrices
arXiv:2110.11840 · doi:10.1016/j.cma.2022.114712
Abstract
Inverse problems involving partial differential equations (PDEs) are widely used in science and engineering. Although such problems are generally ill-posed, different regularisation approaches have been developed to ameliorate this problem. Among them is the Bayesian formulation, where a prior probability measure is placed on the quantity of interest. The resulting posterior probability measure is usually analytically intractable. The Markov Chain Monte Carlo (MCMC) method has been the go-to method for sampling from those posterior measures. MCMC is computationally infeasible for large-scale problems that arise in engineering practice. Lately, Variational Bayes (VB) has been recognised as a more computationally tractable method for Bayesian inference, approximating a Bayesian posterior distribution with a simpler trial distribution by solving an optimisation problem. In this work, we argue, through an empirical assessment, that VB methods are a flexible and efficient alternative to MCMC for this class of problems. We propose a natural choice of a family of Gaussian trial distributions parametrised by precision matrices, thus taking advantage of the inherent sparsity of the inverse problem encoded in its finite element discretisation. We utilise stochastic optimisation to efficiently estimate the variational objective and assess not only the error in the solution mean but also the ability to quantify the uncertainty of the estimate. We test this on PDEs based on the Poisson equation in 1D and 2D. A Tensorflow implementation is made publicly available on GitHub.
References in corpus (25)
- Auto-Encoding Variational Bayes
- Variational Inference: A Review for Statisticians
- On the Convergence of Adam and Beyond
- Gaussian Processes for Big Data
- Frequentist Consistency of Variational Bayes
- Bayesian System Identification based on Hierarchical Sparse Bayesian Learning and Gibbs Sampling with Application to Structural Damage Assessment
- Geometric MCMC for Infinite-Dimensional Inverse Problems
- Functional Variational Bayesian Neural Networks
- Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (2013)
- The statistical finite element method (statFEM) for coherent synthesis of observation data and model predictions
- Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
- Fast Variational Inference in the Conjugate Exponential Family
- Bayesian inference and model comparison for metallic fatigue data
- Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction
- Covariances, Robustness, and Variational Bayes
- Gaussian variational approximation with sparse precision matrices
- Hessian-based adaptive sparse quadrature for infinite-dimensional Bayesian inverse problems
- PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation
- Approximate Bayesian Model Inversion for PDEs with Heterogeneous and State-Dependent Coefficients
- Optimal Bayesian experimental design for subsurface flow problems
- A probabilistic finite element method based on random meshes: Error estimators and Bayesian inverse problems
- Enforcing Boundary Conditions on Physical Fields in Bayesian Inversion
- Bayesian Modeling of Inconsistent Plastic Response due to Material Variability
- Banded Matrix Operators for Gaussian Markov Models in the Automatic Differentiation Era
- A benchmark for the Bayesian inversion of coefficients in partial differential equations