Efficient D-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems
From MaRDI portal
Publication:4683935
DOI10.1137/17M115712XzbMATH Open1401.62123arXiv1711.05878WikidataQ129240688 ScholiaQ129240688MaRDI QIDQ4683935FDOQ4683935
Authors: Alen Alexanderian, Arvind K. Saibaba 
Publication date: 26 September 2018
Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)
Abstract: We develop a computational framework for D-optimal experimental design for PDE-based Bayesian linear inverse problems with infinite-dimensional parameters. We follow a formulation of the experimental design problem that remains valid in the infinite-dimensional limit. The optimal design is obtained by solving an optimization problem that involves repeated evaluation of the log-determinant of high-dimensional operators along with their derivatives. Forming and manipulating these operators is computationally prohibitive for large-scale problems. Our methods exploit the low-rank structure in the inverse problem in three different ways, yielding efficient algorithms. Our main approach is to use randomized estimators for computing the D-optimal criterion, its derivative, as well as the Kullback--Leibler divergence from posterior to prior. Two other alternatives are proposed based on a low-rank approximation of the prior-preconditioned data misfit Hessian, and a fixed low-rank approximation of the prior-preconditioned forward operator. Detailed error analysis is provided for each of the methods, and their effectiveness is demonstrated on a model sensor placement problem for initial state reconstruction in a time-dependent advection-diffusion equation in two space dimensions.
Full work available at URL: https://arxiv.org/abs/1711.05878
Recommendations
- A-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems with regularized \(\ell_0\)-sparsification
- On Bayesian A- and D-optimal experimental designs in infinite dimensions
- Optimal experimental design under irreducible uncertainty for linear inverse problems governed by PDEs
- A Fast and Scalable Computational Framework for Large-Scale High-Dimensional Bayesian Optimal Experimental Design
- Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
uncertainty quantificationlow-rank approximationBayesian inversionlarge-scale ill-posed inverse problemsrandomized matrix methodsD-optimal experimental design
Bayesian inference (62F15) Optimal statistical designs (62K05) PDEs in connection with statistics (35Q62)
Cites Work
- Bayesian experimental design: A review
- Title not available (Why is that?)
- On Information and Sufficiency
- Randomized matrix-free trace and log-determinant estimators
- Title not available (Why is that?)
- Title not available (Why is that?)
- Optimal Measurement Methods for Distributed Parameter System Identification
- Inverse problems: a Bayesian perspective
- Title not available (Why is that?)
- Probability with Martingales
- Schur complements and statistics
- Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix
- Inverse Problem Theory and Methods for Model Parameter Estimation
- Computing $A^\alpha, \log(A)$, and Related Matrix Functions by Contour Integrals
- A computational framework for infinite-dimensional Bayesian inverse problems. I: The linearized case, with application to global seismic inversion
- Title not available (Why is that?)
- Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations
- Numerical methods for optimum experimental design in DAE systems
- Numerical methods for optimal control problems in design of robust optimal experiments for nonlinear dynamic processes
- On Bayesian A- and D-optimal experimental designs in infinite dimensions
- Experimental design for biological systems
- Numerical methods for the design of large-scale nonlinear discrete ill-posed inverse problems
- Numerical methods for experimental design of large-scale linear ill-posed inverse problems
- Numerical methods for \(A\)-optimal designs with a sparsity constraint for ill-posed inverse problems
- Introduction to uncertainty quantification
- GRADIENT-BASED STOCHASTIC OPTIMIZATION METHODS IN BAYESIAN EXPERIMENTAL DESIGN
- Notes on functional analysis
- Mean-variance risk-averse optimal control of systems governed by PDEs with random parameter fields using quadratic approximations
- Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
- A-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems with regularized \(\ell_0\)-sparsification
- A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems
- An algorithm for construction of constrained D-optimum designs
- Multipreconditioned GMRES for shifted systems
- Preconditioned Krylov subspace methods for sampling multivariate Gaussian distributions
- Efficient Bayesian experimentation using an expected information gain lower bound
- Fast Bayesian optimal experimental design for seismic source inversion
- Computing \(f(A)b\) via least squares polynomial approximations
- A-optimal encoding weights for nonlinear inverse problems, with application to the Helmholtz inverse problem
- Experimental design in the context of Tikhonov regularized inverse problems
- Optimal experimental design for inverse problems with state constraints
Cited In (36)
- Multilevel double loop Monte Carlo and stochastic collocation methods with importance sampling for Bayesian optimal experimental design
- A Fast and Scalable Computational Framework for Large-Scale High-Dimensional Bayesian Optimal Experimental Design
- Adaptive A-optimal experimental design for linear dynamical systems
- Sequentially optimized projections in x-ray imaging
- Fast Bayesian optimal experimental design for seismic source inversion
- Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
- Optimal design of simultaneous source encoding
- A greedy sensor selection algorithm for hyperparameterized linear Bayesian inverse problems with correlated noise models
- Uncertainty Quantification and Experimental Design for Large-Scale Linear Inverse Problems under Gaussian Process Priors
- A-optimal encoding weights for nonlinear inverse problems, with application to the Helmholtz inverse problem
- Optimal experimental design: formulations and computations
- Multimodal information gain in Bayesian design of experiments
- Identification of model uncertainty via optimal design of experiments applied to a mechanical press
- Optimal Experimental Design for Inverse Problems in the Presence of Observation Correlations
- PyOED: an extensible suite for data assimilation and model-constrained optimal design of experiments
- Learning physics-based models from data: perspectives from inverse problems and model reduction
- Stochastic learning approach for binary optimization: application to Bayesian optimal design of experiments
- An Offline-Online Decomposition Method for Efficient Linear Bayesian Goal-Oriented Optimal Experimental Design: Application to Optimal Sensor Placement
- Optimal experimental design for inverse problems with state constraints
- Randomization and reweighted \(\ell_1\)-minimization for A-optimal design of linear inverse problems
- Optimal design of large-scale Bayesian linear inverse problems under reducible model uncertainty: good to know what you don't know
- Hyper-differential sensitivity analysis for inverse problems constrained by partial differential equations
- Goal-oriented optimal design of experiments for large-scale Bayesian linear inverse problems
- Edge-promoting adaptive Bayesian experimental design for X-ray imaging
- Guided Bayesian optimal experimental design
- Sequential design of computer experiments for the solution of Bayesian inverse problems
- Optimal experimental design under irreducible uncertainty for linear inverse problems governed by PDEs
- Monte Carlo estimators for the Schatten \(p\)-norm of symmetric positive semidefinite matrices
- Numerical methods for experimental design of large-scale linear ill-posed inverse problems
- Optimal experimental design for prediction based on push-forward probability measures
- Efficient iterative methods for hyperparameter estimation in large-scale linear inverse problems
- A sequential sensor selection strategy for hyper-parameterized linear Bayesian inverse problems
- On Bayesian A- and D-optimal experimental designs in infinite dimensions
- Optimal active experimental design by inverse invariant embedding
- Numerical methods for the design of large-scale nonlinear discrete ill-posed inverse problems
- A-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems with regularized \(\ell_0\)-sparsification
Uses Software
This page was built for publication: Efficient D-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4683935)
