Efficient Bayesian experimentation using an expected information gain lower bound
From MaRDI portal
Abstract: Experimental design is crucial for inference where limitations in the data collection procedure are present due to cost or other restrictions. Optimal experimental designs determine parameters that in some appropriate sense make the data the most informative possible. In a Bayesian setting this is translated to updating to the best possible posterior. Information theoretic arguments have led to the formation of the expected information gain as a design criterion. This can be evaluated mainly by Monte Carlo sampling and maximized by using stochastic approximation methods, both known for being computationally expensive tasks. We propose a framework where a lower bound of the expected information gain is used as an alternative design criterion. In addition to alleviating the computational burden, this also addresses issues concerning estimation bias. The problem of permeability inference in a large contaminated area is used to demonstrate the validity of our approach where we employ the massively parallel version of the multiphase multicomponent simulator TOUGH2 to simulate contaminant transport and a Polynomial Chaos approximation of the forward model that further accelerates the objective function evaluations. The proposed methodology is demonstrated to a setting where field measurements are available.
Recommendations
- Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
- Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
- Surrogate-based sequential Bayesian experimental design using non-stationary Gaussian processes
- Optimal Bayesian experimental design for subsurface flow problems
- Guided Bayesian optimal experimental design
Cites work
- A Stochastic Approximation Method
- An adaptive Metropolis algorithm
- Bayesian experimental design: A review
- Compressive sampling of polynomial chaos expansions: convergence analysis and sampling strategies
- Equation of state calculations by fast computing machines
- Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
- Gaussian processes for machine learning.
- GRADIENT-BASED STOCHASTIC OPTIMIZATION METHODS IN BAYESIAN EXPERIMENTAL DESIGN
- scientific article; zbMATH DE number 50675 (Why is no real title available?)
- scientific article; zbMATH DE number 1262778 (Why is no real title available?)
- scientific article; zbMATH DE number 1941665 (Why is no real title available?)
- Introduction to uncertainty quantification
- Inverse problems: a Bayesian perspective
- Maximum Entropy Sampling and Optimal Bayesian Experimental Design
- Modeling uncertainty in flow simulations via generalized polynomial chaos.
- Monte Carlo sampling methods using Markov chains and their applications
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- On a Measure of the Information Provided by an Experiment
- On Information and Sufficiency
- On the stability and accuracy of least squares approximations
- Optimum experimental designs, with SAS
- Perturbation analysis and optimization of queueing networks
- Physical Systems with Random Uncertainties: Chaos Representations with Arbitrary Probability Measure
- Stochastic Estimation of the Maximum of a Regression Function
- The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
Cited in
(16)- Reduced Wiener chaos representation of random fields via basis adaptation and projection
- The stochastic quasi-chemical model for bacterial growth: variational Bayesian parameter update
- Optimal Bayesian experimental design for subsurface flow problems
- Optimal Bayesian experimental design for electrical impedance tomography in medical imaging
- Multimodal information gain in Bayesian design of experiments
- Adaptive method for indirect identification of the statistical properties of random fields in a Bayesian framework
- Compressive sensing adaptation for polynomial chaos expansions
- An extended polynomial chaos expansion for PDF characterization and variation with aleatory and epistemic uncertainties
- Surrogate-based sequential Bayesian experimental design using non-stationary Gaussian processes
- Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
- Multilevel Monte Carlo estimation of expected information gains
- Bayesian adaptation of chaos representations using variational inference and sampling on geodesics
- Efficient D-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems
- Parallel simultaneous perturbation optimization
- Bayesian sequential optimal experimental design for nonlinear models using policy gradient reinforcement learning
- Multilevel double loop Monte Carlo and stochastic collocation methods with importance sampling for Bayesian optimal experimental design
This page was built for publication: Efficient Bayesian experimentation using an expected information gain lower bound
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5269853)
