GAN-Based Priors for Quantifying Uncertainty in Supervised Learning

DOI10.1137/20M1354210zbMath1473.62092OpenAlexW3204346030MaRDI QIDQ5158923

Dhruv Patel, Assad A. Oberai

Publication date: 26 October 2021

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/20m1354210

zbMATH Keywords

Bayesian inferenceMarkov chain Monte Carlo (MCMC)machine learningactive learninguncertainty quantificationmodel order reductiongenerative adversarial network (GAN)Hamiltonian Monte Carlo (HMC)

Mathematics Subject Classification ID

Software, source code, etc. for problems pertaining to statistics (62-04) Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Reasoning under uncertainty in the context of artificial intelligence (68T37)

Related Items (5)

Learning functional priors and posteriors from data and physics ⋮ Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons ⋮ A dimension-reduced variational approach for solving physics-based inverse problems using generative adversarial network priors and normalizing flows ⋮ Resolution-independent generative models based on operator learning for physics-constrained Bayesian inverse problems ⋮ Solution of physics-based Bayesian inverse problems with deep generative priors

Uses Software

• FEniCS
• MNIST
• TensorFlow
• SegNet
• Wasserstein GAN
• f-GAN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Space-filling curves
• Circumventing the solution of inverse problems in mechanics through deep learning: application to elasticity imaging
• Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
• Data-driven priors and their posterior concentration rates
• On the Brittleness of Bayesian Inference
• Uncertainty Quantification and Polynomial Chaos Techniques in Computational Fluid Dynamics
• Electrical impedance tomography with basis constraints
• Qualitative Robustness in Bayesian Inference
• Machine learning for quantitative finance: fast derivative pricing, hedging and fitting
• Deep learning for finance: deep portfolios
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Solving inverse problems using data-driven models
• Uncertainty, Information, and Sequential Experiments
• Priorconditioners for linear systems
• Optimal Transport

This page was built for publication: GAN-Based Priors for Quantifying Uncertainty in Supervised Learning