Optimal uncertainty quantification
From MaRDI portal
Abstract: We propose a rigorous framework for Uncertainty Quantification (UQ) in which the UQ objectives and the assumptions/information set are brought to the forefront. This framework, which we call emph{Optimal Uncertainty Quantification} (OUQ), is based on the observation that, given a set of assumptions and information about the problem, there exist optimal bounds on uncertainties: these are obtained as values of well-defined optimization problems corresponding to extremizing probabilities of failure, or of deviations, subject to the constraints imposed by the scenarios compatible with the assumptions and information. In particular, this framework does not implicitly impose inappropriate assumptions, nor does it repudiate relevant information. Although OUQ optimization problems are extremely large, we show that under general conditions they have finite-dimensional reductions. As an application, we develop emph{Optimal Concentration Inequalities} (OCI) of Hoeffding and McDiarmid type. Surprisingly, these results show that uncertainties in input parameters, which propagate to output uncertainties in the classical sensitivity analysis paradigm, may fail to do so if the transfer functions (or probability distributions) are imperfectly known. We show how, for hierarchical structures, this phenomenon may lead to the non-propagation of uncertainties or information across scales. In addition, a general algorithmic framework is developed for OUQ and is tested on the Caltech surrogate model for hypervelocity impact and on the seismic safety assessment of truss structures, suggesting the feasibility of the framework for important complex systems. The introduction of this paper provides both an overview of the paper and a self-contained mini-tutorial about basic concepts and issues of UQ.
The authors discuss so called certification problems \(\mathbb{P}[G(X) \geq a] \leq \epsilon\), which means the problem of showing that with probabilty at least \(1-\epsilon\) a response function \(G\) of a given system will not exceed a given safety threshold \(a\). Since \(\mathbb{P}\) and \(G\) often not known a priori, they introduce the set \(\mathcal{A}\) of all admissible scenarios \((f,\mu)\) for the unknown reality \((G,\mathbb{P})\) and investigate the inequality \(\inf_{(f,\mu)\in\mathcal{A}} \mu[f(X) \geq a] \leq \mathbb{P}[G(X) \geq a] \leq \sup_{(f,\mu)\in\mathcal{A}} \mu[f(X) \geq a]\). Within this framework, the authors discuss the problem of uncertainty quantification methodologically and mathematically. Under certain assumptions, they prove reduction theorems which allow reduction to finite dimensional optimization problems. Further, using McDiarmid's inequality and Hoeffding's inequality, they present socalled optimal concentration inequalities. In some cases, they find nonpropagation of uncertainties. The results are applied in detail to practical examples e.g. to Small Particle Hypervelocity Impact Range facilities, to the Seismic Safety Assessment of Structures and to Transport in Porous Media.
Recommendations
- Optimal uncertainty quantification for legacy data observations of Lipschitz functions
- Convex optimal uncertainty quantification
- Uncertainty quantification via codimension-one partitioning
- Introduction to uncertainty quantification
- Distinguishing and integrating aleatoric and epistemic variation in uncertainty quantification
Cited in
(53)- Uncertainties in parameter estimation: The optimal experiment design
- Uncertainty quantification by geometric characterization of sensitivity spaces
- Scalable information inequalities for uncertainty quantification
- Ensemble Kalman filters and geometric characterization of sensitivity spaces for uncertainty quantification in optimization
- An optimal point estimate method for uncertainty studies. (Discussion paper)
- Volumetric uncertainty bounds and optimal configurations for converging beam triple LIDAR
- A comparison of stochastic and data-driven FEM approaches to problems with insufficient material data
- Data fusion for uncertainty quantification with non-intrusive polynomial chaos
- Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods
- Uncertainty quantification of the 4th kind; optimal posterior accuracy-uncertainty tradeoff with the minimum enclosing ball
- Probability estimation via policy restrictions, convexification, and approximate sampling
- A distributionally robust perspective on uncertainty quantification and chance constrained programming
- A Hankel norm for quadrature rules solving random linear dynamical systems
- Brittleness of Bayesian inference under finite information in a continuous world
- Rigorous verification, validation, uncertainty quantification and certification through concentration-of-measure inequalities
- Numerical upscaling of parametric microstructures in a possibilistic uncertainty framework with tensor trains
- On the brittleness of Bayesian inference
- Elimination of the type B uncertainty
- Multigrid with Rough Coefficients and Multiresolution Operator Decomposition from Hierarchical Information Games
- Uncertainty quantification via codimension-one partitioning
- Numerical accuracy and efficiency in the propagation of epistemic and aleatory uncertainties
- Uncertainty quantification in graph-based classification of high dimensional data
- Comparison of statistical and deterministic frameworks of uncertainty quantification
- A novel model predictive controller for uncertain constrained systems
- A dynamically bi-orthogonal method for time-dependent stochastic partial differential equations. I: Derivation and algorithms
- Optimum statistical estimates in conditions of ambiguity
- Measuring the unmeasurable: an application of uncertainty quantification to treasury bond portfolios
- Ambiguous joint chance constraints under mean and dispersion information
- Robust Information Divergences for Model-Form Uncertainty Arising from Sparse Data in Random PDE
- Optimality, identifiability, and sensitivity
- Consistent Uncertainty Reduction in Modeling Nonlinear Systems
- Spectral analysis for uncertainty quantification
- Lattice Boltzmann method for stochastic convection-diffusion equations
- Quantification of model uncertainty on path-space via goal-oriented relative entropy
- Model Uncertainty and Correctability for Directed Graphical Models
- Wasserstein sensitivity of risk and uncertainty propagation
- Optimization of quasi-convex function over product measure sets
- Uncertainty quantification for computer models with spatial output using calibration-optimal bases
- Chebyshev inequalities for products of random variables
- Fuzzy-stochastic partial differential equations
- On the application of McDiarmid's inequality to complex systems
- Distinguishing and integrating aleatoric and epistemic variation in uncertainty quantification
- Optimal uncertainty quantification for legacy data observations of Lipschitz functions
- Convex optimal uncertainty quantification
- Collaborative and adaptive Bayesian optimization for bounding variances and probabilities under hybrid uncertainties
- An Information Geometry Approach to Robustness Analysis for the Uncertainty Quantification of Computer Codes
- Efficient uncertainty quantification for mechanical properties of randomly perturbed elastic rods
- Democratizing uncertainty quantification
- Distributionally robust optimization
- Distributionally robust optimal uncertainty quantification under Phi-divergence ambiguity
- Optimal unpredictable control for linear systems
- \(\Pi\)4U: a high performance computing framework for Bayesian uncertainty quantification of complex models
- Brittleness of Bayesian inference and new Selberg formulas
This page was built for publication: Optimal uncertainty quantification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2840354)
