Probabilistic numerics and uncertainty in computations

DOI10.1098/rspa.2015.0142zbMath1372.65010arXiv1506.01326OpenAlexW3099671035WikidataQ51727939 ScholiaQ51727939MaRDI QIDQ5362455

Michael A. Osborne, Philipp Hennig, Mark A. Girolami

Publication date: 29 September 2017

Published in: Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1506.01326

Mathematics Subject Classification ID

Bayesian inference (62F15) Probabilistic models, generic numerical methods in probability and statistics (65C20) Computational methods for problems pertaining to probability theory (60-08) Reasoning under uncertainty in the context of artificial intelligence (68T37) Roundoff error (65G50)

Related Items

Randomised one-step time integration methods for deterministic operator differential equations, Augmented Gaussian random field: theory and computation, Solving and learning nonlinear PDEs with Gaussian processes, Collocation Methods and Beyond in Non-linear Mechanics, Uncertainty quantification using probabilistic numerics: application to models in mathematical epidemiology, Unnamed Item, Clustering and the efficient use of cognitive resources, Stochastic Parareal: An Application of Probabilistic Methods to Time-Parallelization, Computational graph completion, Adaptive experiment design for probabilistic integration, Inferring solutions of differential equations using noisy multi-fidelity data, Multi-fidelity Gaussian process regression for prediction of random fields, A new second order Taylor-like theorem with an optimized reduced remainder, Subset simulation for probabilistic computer models, Projected regression method for solving Fredholm integral equations arising in the analytic continuation problem of quantum physics, A survey of subspace recycling iterative methods, Statistical properties of BayesCG under the Krylov prior, Multigrid with Rough Coefficients and Multiresolution Operator Decomposition from Hierarchical Information Games, Collaborative and adaptive Bayesian optimization for bounding variances and probabilities under hybrid uncertainties, Probabilistic solvers enable a straight-forward exploration of numerical uncertainty in neuroscience models, Theoretical Guarantees for the Statistical Finite Element Method, Statistical analysis of differential equations: introducing probability measures on numerical solutions, Fully Symmetric Kernel Quadrature, Maximum Likelihood Estimation and Uncertainty Quantification for Gaussian Process Approximation of Deterministic Functions, Bayesian Quadrature, Energy Minimization, and Space-Filling Design, Random Forward Models and Log-Likelihoods in Bayesian Inverse Problems, Convergence rates of Gaussian ODE filters, Adaptive reference elements via harmonic extensions and associated inner modes, GPU-accelerated particle methods for evaluation of sparse observations for inverse problems constrained by diffusion PDEs, Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data, Physics-informed cokriging: a Gaussian-process-regression-based multifidelity method for data-model convergence, A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions, Optimality and Regularization Properties of Quasi-Interpolation: Deterministic and Stochastic Approaches, Efficient acquisition rules for model-based approximate Bayesian computation, Multivariate Monte Carlo Approximation Based on Scattered Data, A probabilistic finite element method based on random meshes: a posteriori error estimators and Bayesian inverse problems, Bayes linear analysis for ordinary differential equations, Unnamed Item, Gamblets for opening the complexity-bottleneck of implicit schemes for hyperbolic and parabolic ODEs/PDEs with rough coefficients, Practical Hilbert space approximate Bayesian Gaussian processes for probabilistic programming, Unnamed Item, Bayesian Probabilistic Numerical Methods in Time-Dependent State Estimation for Industrial Hydrocyclone Equipment, Scalable high-resolution forecasting of sparse spatiotemporal events with kernel methods: a winning solution to the NIJ ``Real-time crime forecasting challenge, De-noising by thresholding operator adapted wavelets, Symmetry exploits for Bayesian cubature methods, Probabilistic linear solvers: a unifying view, Strong convergence rates of probabilistic integrators for ordinary differential equations, Probabilistic solutions to ordinary differential equations as nonlinear Bayesian filtering: a new perspective, On the positivity and magnitudes of Bayesian quadrature weights, A modern retrospective on probabilistic numerics, A role for symmetry in the Bayesian solution of differential equations, Parallel Gaussian process surrogate Bayesian inference with noisy likelihood evaluations, Bayesian ODE solvers: the maximum a posteriori estimate, Bayesian numerical methods for nonlinear partial differential equations, A supermartingale approach to Gaussian process based sequential design of experiments, Probabilistic integration: a role in statistical computation?, Comment: unreasonable effectiveness of Monte Carlo, Quasi-interpolation for multivariate density estimation on bounded domain, Bayesian Probabilistic Numerical Methods, Model-based kernel sum rule: kernel Bayesian inference with probabilistic models, A Bayesian conjugate gradient method (with discussion), Unnamed Item, Unnamed Item, A probabilistic model for the numerical solution of initial value problems, The SPDE approach to Matérn fields: graph representations, Unnamed Item, Estimation of Ordinary Differential Equation Models with Discretization Error Quantification, Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations, Physics Information Aided Kriging using Stochastic Simulation Models, Probabilistic solutions to DAEs learning from physical data, Stochastic Parareal: An Application of Probabilistic Methods to Time-Parallelization, Do ideas have shape? Idea registration as the continuous limit of artificial neural networks