A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems

@article{Alexanderian2016AFA,
  title={A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems},
  author={Alen Alexanderian and No{\'e}mi Petra and Georg Stadler and Omar Ghattas},
  journal={SIAM J. Sci. Comput.},
  year={2016},
  volume={38}
}
We address the problem of optimal experimental design (OED) for Bayesian nonlinear inverse problems governed by PDEs. The goal is to find a placement of sensors, at which experimental data are collected, so as to minimize the uncertainty in the inferred parameter field. We formulate the OED objective function by generalizing the classical A-optimal experimental design criterion using the expected value of the trace of the posterior covariance. We seek a method that solves the OED problem at a… Expand
A fast and scalable computational framework for large-scale and high-dimensional Bayesian optimal experimental design
TLDR
A fast and scalable computational framework to solve large-scale and high-dimensional Bayesian optimal experimental design problems and proposes an efficient offline-online decomposition for the optimization problem, which is formulated as an optimization problem that seeks to maximize an expected information gain. Expand
Efficient D-Optimal Design of Experiments for Infinite-Dimensional Bayesian Linear Inverse Problems
TLDR
A computational framework for D-optimal experimental design for PDE-based Bayesian linear inverse problems with infinite-dimensional parameters is developed, to use randomized estimators for computing the D-Optimal criterion, its derivative, as well as the Kullback--Leibler divergence from posterior to prior. Expand
Optimal Experimental Design for Constrained Inverse Problems
In this paper, we address the challenging problem of optimal experimental design (OED) of constrained inverse problems. We consider two OED formulations that allow reducing the experimental costs byExpand
A fast and scalable computational framework for goal-oriented linear Bayesian optimal experimental design: Application to optimal sensor placement
TLDR
This work develops a fast and scalable computational framework for goal-oriented OED of large-scale Bayesian linear inverse problems that finds sensor locations to maximize the expected information gain (EIG) for a predicted quantity of interest. Expand
Goal-Oriented Optimal Design of Experiments for Large-Scale Bayesian Linear Inverse Problems
TLDR
This work develops a framework for goal oriented optimal design of experiments (GOODE) for large-scale Bayesian linear inverse problems governed by PDEs, and develops an efficient gradient-based optimization framework for solving the GOODE optimization problems. Expand
Optimal Bayesian experiment design for nonlinear dynamic systems with chance constraints
TLDR
A novel surrogate model based on arbitrary polynomial chaos (aPC) is proposed, which readily applies to any type of prior distribution and appears to have the potential to pave the way for real-time or sequential dynamic experiment design in a fully Bayesian setting. Expand
Multidimensional sum-up rounding for integer programming in optimal experimental design
  • Jing Yu, M. Anitescu
  • Computer Science, Mathematics
  • Math. Program.
  • 2021
TLDR
Asymptotic optimality of the integer solution defining the upper bound for different experimental design criteria (A- and D-optimal), by proving the convergence to zero of the gap between the upper and lower bounds as the mesh size goes to zero is shown. Expand
Taylor approximation and variance reduction for PDE-constrained optimal control under uncertainty
TLDR
A scalable computational framework for the solution of PDE-constrained optimal control problems under high-dimensional uncertainty and uses the Lagrangian formalism to derive expressions for the gradient with respect to the control and applies a gradient-based optimization method to solve the problem. Expand
Optimal Experimental Design Using A Consistent Bayesian Approach
TLDR
The formulation is based on the recently developed consistent Bayesian approach for solving stochastic inverse problems which seeks a posterior probability density that is consistent with the model and the data in the sense that the push-forward of the posterior matches the observed density on the observations almost everywhere. Expand
A-optimal encoding weights for nonlinear inverse problems, with application to the Helmholtz inverse problem
The computational cost of solving an inverse problem governed by PDEs, using multiple experiments, increases linearly with the number of experiments. A recently proposed method to decrease this costExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
A-Optimal Design of Experiments for Infinite-Dimensional Bayesian Linear Inverse Problems with Regularized ℓ0-Sparsification
TLDR
It is found that an optimal design can be computed at a cost, measured in number of forward PDE solves, that is independent of the parameter and sensor dimensions. Expand
GRADIENT-BASED STOCHASTIC OPTIMIZATION METHODS IN BAYESIAN EXPERIMENTAL DESIGN
TLDR
This paper develops gradient-based stochastic optimization methods for the design of experiments on a continuous parameter space from a Bayesian perspective and uses infinitesimal perturbation analysis to derive gradients of a Monte Carlo estimator. Expand
MAP estimators and their consistency in Bayesian nonparametric inverse problems
We consider the inverse problem of estimating an unknown function u from noisy measurements y of a known, possibly nonlinear, map $\mathcal {G}$ applied to u. We adopt a Bayesian approach to theExpand
Fast Algorithms for Bayesian Uncertainty Quantification in Large-Scale Linear Inverse Problems Based on Low-Rank Partial Hessian Approximations
TLDR
It is demonstrated that the number of forward PDE solves required for an accurate low-rank approximation is independent of the problem dimension, which permits scalable estimation of the uncertainty in large-scale ill-posed linear inverse problems at a small multiple of the cost of solving the forward problem. Expand
Simulation-based optimal Bayesian experimental design for nonlinear systems
TLDR
This work proposes a general mathematical framework and an algorithmic approach for optimal experimental design with nonlinear simulation-based models, and focuses on finding sets of experiments that provide the most information about targeted sets of parameters. Expand
A Computational Framework for Infinite-Dimensional Bayesian Inverse Problems Part I: The Linearized Case, with Application to Global Seismic Inversion
TLDR
A computational framework for estimating the uncertainty in the numerical solution of linearized infinite-dimensional statistical inverse problems that incorporates algorithms for manipulating the prior, constructing a low rank approximation of the data-informed component of the posterior covariance operator, and exploring the posterior that together ensure scalability of the entire framework to very high parameter dimensions. Expand
Besov priors for Bayesian inverse problems
We consider the inverse problem of estimating a function $u$ from noisy, possibly nonlinear, observations. We adopt a Bayesian approach to the problem. This approach has a long history for inversion,Expand
IBM Research Report Numerical Methods for the Design of Large-Scale Nonlinear Discrete Ill-Posed Inverse Problems
TLDR
This work presents an algorithmic framework for nonlinear experimental design with an efficient numerical implementation and demonstrates the viability of the design with a problem in electromagnetic imaging based on direct current resistivity and magnetotelluric data. Expand
Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
Shannon-type expected information gain can be used to evaluate the relevance of a proposed experiment subjected to uncertainty. The estimation of such gain, however, relies on a double-loopExpand
Numerical methods for A-optimal designs with a sparsity constraint for ill-posed inverse problems
TLDR
The minimization of the objective function in the classic A-optimal design is generalized to a Bayes risk minimization with a sparsity constraint and efficient algorithms for applications of such designs to large-scale problems are presented. Expand
...
1
2
3
4
...