Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems

DOI10.1007/s00466-019-01718-yzbMath1471.74074arXiv1901.04878OpenAlexW2963716063WikidataQ113327095 ScholiaQ113327095MaRDI QIDQ2319398

Paris Perdikaris, Yibo Yang

Publication date: 19 August 2019

Published in: Computational Mechanics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.04878

zbMATH Keywords

dynamical systemvariational inferencemulti-fidelity modelinggenerative adversarial networkprobabilistic deep learningdata-driven surrogate

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamical problems in solid mechanics (74H99) Stochastic and other probabilistic methods applied to problems in solid mechanics (74S60)

Related Items (11)

A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables ⋮ Robust topology optimization with low rank approximation using artificial neural networks ⋮ Deep capsule encoder–decoder network for surrogate modeling and uncertainty quantification ⋮ Fully probabilistic deep models for forward and inverse problems in parametric PDEs ⋮ Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons ⋮ Isogeometric neural networks: a new deep learning approach for solving parameterized partial differential equations ⋮ A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the small data regime ⋮ Bayesian differential programming for robust systems identification under uncertainty ⋮ An encoder-decoder deep surrogate for reverse time migration in seismic imaging under uncertainty ⋮ Interpretable machine learning: fundamental principles and 10 grand challenges ⋮ Unnamed Item

Uses Software

• TensorFlow
• ImageNet
• Adam
• AlexNet
• Wasserstein GAN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• AlexNet
• Multi-output separable Gaussian process: towards an efficient, fully Bayesian paradigm for uncertainty quantification
• Bayesian inference with optimal maps
• Multi-fidelity Gaussian process regression for prediction of random fields
• Bayesian learning for neural networks
• Adversarial uncertainty quantification in physics-informed neural networks
• A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the small data regime
• Multifidelity importance sampling
• Optimal Model Management for Multifidelity Monte Carlo Estimation
• A Stochastic Collocation Algorithm with Multifidelity Models
• Computational Aspects of Stochastic Collocation with Multifidelity Models
• Multi-fidelity optimization via surrogate modelling
• Graphical Models, Exponential Families, and Variational Inference
• Survey of Multifidelity Methods in Uncertainty Propagation, Inference, and Optimization
• Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling
• Predicting the output from a complex computer code when fast approximations are available
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Fourth-Order Time-Stepping for Stiff PDEs
• Advanced Lectures on Machine Learning
• Multifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data sets
• Optimal Transport
• The elements of statistical learning. Data mining, inference, and prediction

This page was built for publication: Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems