Solving Large-Scale PDE-constrained Bayesian Inverse Problems with Riemann Manifold Hamiltonian Monte Carlo

Abstract

We consider the Riemann manifold Hamiltonian Monte Carlo (RMHMC) method for solving statistical inverse problems governed by partial differential equations (PDEs). The power of the RMHMC method is that it exploits the geometric structure induced by the PDE constraints of the underlying inverse problem. Consequently, each RMHMC posterior sample is almost independent from the others providing statistically efficient Markov chain simulation. We reduce the cost of forming the Fisher information matrix by using a low rank approximation via a randomized singular value decomposition technique. This is efficient since a small number of Hessian-vector products are required. The Hessian-vector product in turn requires only two extra PDE solves using the adjoint technique. The results suggest RMHMC as a highly efficient simulation scheme for sampling from PDE induced posterior measures.

To Appear in IoP Inverse Problems

Cited by in corpus (18)

• Geometric MCMC for Infinite-Dimensional Inverse Problems
• Accelerating MCMC with active subspaces
• Multilevel Sequential${}^2$ Monte Carlo for Bayesian Inverse Problems
• Emulation of Higher-Order Tensors in Manifold Monte Carlo Methods for Bayesian Inverse Problems
• Bayesian calibration and sensitivity analysis for a karst aquifer model using active subspaces
• Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
• Bayesian inference of heterogeneous epidemic models: Application to COVID-19 spread accounting for long-term care facilities
• Accelerated dimension-independent adaptive Metropolis
• Variational Bayes' method for functions with applications to some inverse problems
• Efficient parameter estimation for a methane hydrate model with active subspaces
• Prior normalization for certified likelihood-informed subspace detection of Bayesian inverse problems
• A Data-Scalable Randomized Misfit Approach for Solving Large-Scale PDE-Constrained Inverse Problems
• Transform-based particle filtering for elliptic Bayesian inverse problems
• Variational Inference for Nonlinear Inverse Problems via Neural Net Kernels: Comparison to Bayesian Neural Networks, Application to Topology Optimization
• High-dimensional Nonlinear Bayesian Inference of Poroelastic Fields from Pressure Data
• Joint Estimation of Robin Coefficient and Domain Boundary for the Poisson Problem
• Sampling parameters of ordinary differential equations with Langevin dynamics that satisfy constraints
• On Unifying Randomized Methods For Inverse Problems