Accelerating Hamiltonian Monte Carlo for Bayesian inference in neural networks and neural operators
- 22 September 2025
- journal article
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 447
Abstract
No abstract availableAll Related Versions
Funding Information
- Air Force Office of Scientific Research
- U.S. Department of Energy
- Office of Science
- Advanced Scientific Computing Research (DE-SC0024162)
This publication has 19 references indexed in Scilit:
- Bayesian neural networks for predicting uncertainty in full-field material responseComputer Methods in Applied Mechanics and Engineering, 2024
- Efficient Bayesian inference with latent Hamiltonian neural networks in No-U-Turn SamplingJournal of Computational Physics, 2023
- Instability-wave prediction in hypersonic boundary layers with physics-informed neural operatorsJournal of Computational Science, 2023
- Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisonsJournal of Computational Physics, 2023
- Neural operator prediction of linear instability waves in high-speed boundary layersJournal of Computational Physics, 2022
- Assimilation of wall-pressure measurements in high-speed flow over a coneJournal of Fluid Mechanics, 2022
- DeepM&Mnet for hypersonics: Predicting the coupled flow and finite-rate chemistry behind a normal shock using neural-network approximation of operatorsJournal of Computational Physics, 2021
- Observation-infused simulations of high-speed boundary-layer transitionJournal of Fluid Mechanics, 2021
- Nonlinearly most dangerous disturbance for high-speed boundary-layer transitionJournal of Fluid Mechanics, 2019
- Sensitivity of high-speed boundary-layer stability to base-flow distortionJournal of Fluid Mechanics, 2018