Data-Driven Model Reduction for the Bayesian Solution of Inverse Problems

Abstract

One of the major challenges in the Bayesian solution of inverse problems governed by partial differential equations (PDEs) is the computational cost of repeatedly evaluating numerical PDE models, as required by Markov chain Monte Carlo (MCMC) methods for posterior sampling. This paper proposes a data-driven projection-based model reduction technique to reduce this computational cost. The proposed technique has two distinctive features. First, the model reduction strategy is tailored to inverse problems: the snapshots used to construct the reduced-order model are computed adaptively from the posterior distribution. Posterior exploration and model reduction are thus pursued simultaneously. Second, to avoid repeated evaluations of the full-scale numerical model as in a standard MCMC method, we couple the full-scale model and the reduced-order model together in the MCMC algorithm. This maintains accurate inference while reducing its overall computational cost. In numerical experiments considering steady-state flow in a porous medium, the data-driven reduced-order model achieves better accuracy than a reduced-order model constructed using the classical approach. It also improves posterior sampling efficiency by several orders of magnitude compared to a standard MCMC method.

Cited by in corpus (26)

• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Adaptive multi-fidelity polynomial chaos approach to Bayesian inference in inverse problems
• Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction
• Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools
• Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion
• Adaptive Multi-index Collocation for Uncertainty Quantification and Sensitivity Analysis
• A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime
• Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
• Bayesian model and dimension reduction for uncertainty propagation: applications in random media
• Deep composition of tensor-trains using squared inverse Rosenblatt transports
• Adaptive Model Refinement Approach for Bayesian Uncertainty Quantification in Turbulence Model
• A Reduced Basis Landweber method for nonlinear inverse problems
• An adaptive reduced basis ANOVA method for high-dimensional Bayesian inverse problems
• Bayesian model inversion using stochastic spectral embedding
• Multifidelity Approximate Bayesian Computation
• Gaussian Process Regression and Conditional Polynomial Chaos for Parameter Estimation
• Neural Ordinary Differential Equations for Model Order Reduction of Stiff Systems
• Data-Driven Forward Discretizations for Bayesian Inversion
• Surrogate Accelerated Bayesian Inversion for the Determination of the Thermal Diffusivity of a Material
• Variational Inference for Nonlinear Inverse Problems via Neural Net Kernels: Comparison to Bayesian Neural Networks, Application to Topology Optimization
• MCMC-Net: Accelerating Markov Chain Monte Carlo with Neural Networks for Inverse Problems
• Joint state-parameter estimation of a nonlinear stochastic energy balance model from sparse noisy data
• Stabilizing and Solving Unique Continuation Problems by Parameterizing Data and Learning Finite Element Solution Operators
• Bayesian Approach to Inverse Time-harmonic Acoustic Scattering from Sound-soft Obstacles with Phaseless Data
• Magnet Resonance Electrical Impedance Tomography (MREIT): Convergence and Reduced Basis Approach
• Reduced Modeling of Unknown Trajectories