Adversarial sampling of unknown and high-dimensional conditional distributions

DOI10.1016/j.jcp.2021.110853OpenAlexW3215893774MaRDI QIDQ2134718

Ryan N. King, Karen Stengel, Andrew Glaws, Malik Hassanaly

Publication date: 3 May 2022

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

Full work available at URL: https://arxiv.org/abs/2111.05962

zbMATH Keywords

turbulencedeconvolutiondeep learninggenerative adversarial networkshigh-dimensional sampling

Mathematics Subject Classification ID

Turbulence (76Fxx) Fluid mechanics (76-XX) Probabilistic methods, stochastic differential equations (65Cxx)

Related Items (1)

Multiscale graph neural network autoencoders for interpretable scientific machine learning

Uses Software

• TensorFlow
• CycleGAN
• pix2pix
• VEEGAN
• Wasserstein GAN
• AdaGAN

Cites Work

• \textit{A priori} analysis of reduced description of dynamical systems using approximate inertial manifolds
• The Frechet distance between multivariate normal distributions
• Implicit subgrid-scale modeling by adaptive deconvolution
• Approximate deconvolution reduced order modeling
• Ensemble forecasting
• Genealogical particle analysis of rare events
• Rare event computation in deterministic chaotic systems using genealogical particle analysis
• Machine Learning for Fluid Mechanics
• Adaptive Multilevel Splitting for Rare Event Analysis
• An approximate deconvolution procedure for large-eddy simulation
• An approximate deconvolution model for large-eddy simulation with application to incompressible wall-bounded flows
• Self-conditioned fields for large-eddy simulations of turbulent flows
• The Calculation of Posterior Distributions by Data Augmentation
• Deterministic Nonperiodic Flow
• Stochastic estimation of conditional structure: a review
• Statistics of turbulence subgrid-scale stresses: Necessary conditions and experimental tests
• Optimal LES formulations for isotropic turbulence
• A posteriori analysis of low-pass spatial filters for approximate deconvolution large eddy simulations of homogeneous incompressible flows
• Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Equation of State Calculations by Fast Computing Machines
• A new deconvolution method for large eddy simulation
• Monte Carlo sampling methods using Markov chains and their applications
• Large Eddy Simulation for Incompressible Flows
• A self-similarity principle for the computation of rare event probability

This page was built for publication: Adversarial sampling of unknown and high-dimensional conditional distributions