Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion

DOI10.1016/J.JCP.2018.12.037zbMath1451.62095arXiv1807.04302OpenAlexW2838828138WikidataQ114666192 ScholiaQ114666192MaRDI QIDQ2214630

Steven Atkinson, Nicholas Zabaras

Publication date: 10 December 2020

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.04302

zbMATH Keywords

Gaussian processesstochastic partial differential equationsBayesian inferenceuncertainty quantificationvariational inferencesurrogate models

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Gaussian processes (60G15) Bayesian inference (62F15) Inverse problems for PDEs (35R30) PDEs with randomness, stochastic partial differential equations (35R60)

Related Items (13)

Calibrate, emulate, sample ⋮ Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems ⋮ Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data ⋮ A bi-fidelity surrogate modeling approach for uncertainty propagation in three-dimensional hemodynamic simulations ⋮ Transformers for modeling physical systems ⋮ Conditional variational autoencoder with Gaussian process regression recognition for parametric models ⋮ Data-driven spatiotemporal modeling for structural dynamics on irregular domains by stochastic dependency neural estimation ⋮ Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data ⋮ A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the small data regime ⋮ A Low-Rank Approximated Multiscale Method for Pdes With Random Coefficients ⋮ Bayesian learning of orthogonal embeddings for multi-fidelity Gaussian processes ⋮ Surrogate assisted active subspace and active subspace assisted surrogate -- a new paradigm for high dimensional structural reliability analysis ⋮ A novel sequential method to train physics informed neural networks for Allen Cahn and Cahn Hilliard equations

Uses Software

• mftoolbox
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-output separable Gaussian process: towards an efficient, fully Bayesian paradigm for uncertainty quantification
• Stochastic spectral methods for efficient Bayesian solution of inverse problems
• A non-linear dimension reduction methodology for generating data-driven stochastic input models
• Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
• PRMLT
• A Bayesian approach to multiscale inverse problems with on-the-fly scale determination
• Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
• Multivariate sensitivity analysis of saturated flow through simulated highly heterogeneous groundwater aquifers
• Bayesian Calibration of Computer Models
• A Stochastic Newton MCMC Method for Large-Scale Statistical Inverse Problems with Application to Seismic Inversion
• An Introduction to Computational Stochastic PDEs
• Data-driven model reduction for the Bayesian solution of inverse problems
• Kronecker products and matrix calculus in system theory
• Markov Chain Monte Carlo Methods for High Dimensional Inversion in Remote Sensing
• Solution of inverse problems with limited forward solver evaluations: a Bayesian perspective
• Modelling of Multiscale Structures in Flow Simulations for Petroleum Reservoirs
• Functions of Matrices

This page was built for publication: Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion