Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations

DOI10.1016/j.cma.2013.02.017zbMath1286.62068MaRDI QIDQ2449911

Suojin Wang, Marco Scavino, Raúl Tempone, Quan Long

Publication date: 13 May 2014

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cma.2013.02.017

zbMATH Keywords

Bayesian statistics; Monte Carlo sampling; Laplace approximation; uncertainty quantification; information gain; Bayesian experimental design; sparse quadrature

Mathematics Subject Classification ID

62K05: Optimal statistical designs

62F15: Bayesian inference

65C20: Probabilistic models, generic numerical methods in probability and statistics

65N21: Numerical methods for inverse problems for boundary value problems involving PDEs

Related Items

Goal-oriented optimal design of experiments for large-scale Bayesian linear inverse problems, Efficient D-Optimal Design of Experiments for Infinite-Dimensional Bayesian Linear Inverse Problems, Sequentially optimized projections in x-ray imaging ^*, Unbiased MLMC Stochastic Gradient-Based Optimization of Bayesian Experimental Designs, Hyper-differential sensitivity analysis for inverse problems constrained by partial differential equations, Efficient Bayesian Experimentation Using an Expected Information Gain Lower Bound, Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review, Edge-Promoting Adaptive Bayesian Experimental Design for X-ray Imaging, An Offline-Online Decomposition Method for Efficient Linear Bayesian Goal-Oriented Optimal Experimental Design: Application to Optimal Sensor Placement, A Review of Modern Computational Algorithms for Bayesian Optimal Design, A Fast and Scalable Computational Framework for Large-Scale High-Dimensional Bayesian Optimal Experimental Design, A greedy sensor selection algorithm for hyperparameterized linear Bayesian inverse problems with correlated noise models, Large-scale Bayesian optimal experimental design with derivative-informed projected neural network, Optimal design of validation experiments for the prediction of quantities of interest, Bayesian design for minimizing prediction uncertainty in bivariate spatial responses with applications to air quality monitoring, Bayesian decision-theoretic design of experiments under an alternative model, Optimal experimental design for prediction based on push-forward probability measures, An approach for finding fully Bayesian optimal designs using normal-based approximations to loss functions, Fast Bayesian optimal experimental design for seismic source inversion, Principles of experimental design for big data analysis, A Laplace method for under-determined Bayesian optimal experimental designs, On the value of test data for reducing uncertainty in material models: computational framework and application to spherical indentation, A state estimation approach based on stochastic expansions, Optimal Bayesian experimental design for subsurface flow problems, Optimal Bayesian experimental design for electrical impedance tomography in medical imaging, Approximate Laplace importance sampling for the estimation of expected Shannon information gain in high-dimensional Bayesian design for nonlinear models, Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems, Multimodal information gain in Bayesian design of experiments, On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems, A Laplace-based algorithm for Bayesian adaptive design, Surrogate-based sequential Bayesian experimental design using non-stationary Gaussian processes, Bayesian design of experiments for intractable likelihood models using coupled auxiliary models and multivariate emulation, Calibration experimental design considering field response and model uncertainty, Nesterov-aided stochastic gradient methods using Laplace approximation for Bayesian design optimization, Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain, Gaussian process surrogates for failure detection: a Bayesian experimental design approach, Small-noise approximation for Bayesian optimal experimental design with nuisance uncertainty, Multilevel Monte Carlo estimation of expected information gains, Optimal experimental design under irreducible uncertainty for linear inverse problems governed by PDEs, A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems

Cites Work