Goal-Oriented Optimal Design of Experiments for Large-Scale Bayesian Linear Inverse Problems

Abstract

We develop a framework for goal-oriented optimal design of experiments (GOODE) for large-scale Bayesian linear inverse problems governed by PDEs. This framework differs from classical Bayesian optimal design of experiments (ODE) in the following sense: we seek experimental designs that minimize the posterior uncertainty in the experiment end-goal, e.g., a quantity of interest (QoI), rather than the estimated parameter itself. This is suitable for scenarios in which the solution of an inverse problem is an intermediate step and the estimated parameter is then used to compute a QoI. In such problems, a GOODE approach has two benefits: the designs can avoid wastage of experimental resources by a targeted collection of data, and the resulting design criteria are computationally easier to evaluate due to the often low-dimensionality of the QoIs. We present two modified design criteria, A-GOODE and D-GOODE, which are natural analogues of classical Bayesian A- and D-optimal criteria. We analyze the connections to other ODE criteria, and provide interpretations for the GOODE criteria by using tools from information theory. Then, we develop an efficient gradient-based optimization framework for solving the GOODE optimization problems. Additionally, we present comprehensive numerical experiments testing the various aspects of the presented approach. The driving application is the optimal placement of sensors to identify the source of contaminants in a diffusion and transport problem. We enforce sparsity of the sensor placements using an ${\ell }_1$-norm penalty approach, and propose a practical strategy for specifying the associated penalty parameter.

25 pages, 13 figures

References in corpus (5)

• Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
• A-optimal encoding weights for nonlinear inverse problems, with applications to the Helmholtz inverse problem
• The Reduced-Order Hybrid Monte Carlo Sampling Smoother
• Optimal Experimental Design Using A Consistent Bayesian Approach
• Optimal Experimental Design for Constrained Inverse Problems

Cited by in corpus (11)

• Variational Bayesian experimental design for geophysical applications: seismic source location, amplitude versus offset inversion, and estimating CO2 saturations in a subsurface reservoir
• Optimal experimental design under irreducible uncertainty for linear inverse problems governed by PDEs
• Stochastic Learning Approach to Binary Optimization for Optimal Design of Experiments
• A fast and scalable computational framework for large-scale and high-dimensional Bayesian optimal experimental design
• Sequentially optimized projections in X-ray imaging
• Where to Drill Next? A Dual-Weighted Approach to Adaptive Optimal Design of Groundwater Surveys
• Variational Sequential Optimal Experimental Design using Reinforcement Learning
• Variance-based sensitivity of Bayesian inverse problems to the prior distribution
• An Optimal Experimental Design Framework for Adaptive Inflation and Covariance Localization for Ensemble Filters
• Goal-Oriented Bayesian Optimal Experimental Design for Nonlinear Models using Markov Chain Monte Carlo
• Sparse Source Identification in Transient Advection-Diffusion Problems with a Primal-Dual-Active-Point Strategy