Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-informed Deep Generative Models

DOI10.1137/21M1413018zbMath1491.60117arXiv2008.01915OpenAlexW3138463430MaRDI QIDQ5022489

No author found.

Publication date: 19 January 2022

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.01915

zbMATH Keywords

generative adversarial networksstochastic ODEsdynamic inferencephysics-informed learningnonlocal flocking dynamics

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Markov processes: estimation; hidden Markov models (62M05) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)

Related Items (2)

Data-driven method to learn the most probable transition pathway and stochastic differential equation ⋮ Detecting stochastic governing laws with observation on stationary distributions

Uses Software

• Adam
• torchdiffeq
• torchsde
• Wasserstein GAN

Cites Work

• Unnamed Item
• \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
• Estimating parameters in stochastic systems: A variational Bayesian approach
• Data-driven discovery of coarse-grained equations
• Adversarial uncertainty quantification in physics-informed neural networks
• Nonlocal flocking dynamics: learning the fractional order of PDEs from particle simulations
• Likelihood Inference for Discretely Observed Nonlinear Diffusions
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Emergent Behavior in Flocks
• Hamiltonian ODEs in the Wasserstein space of probability measures
• Posterior inference on parameters of stochastic differential equations via non-linear Gaussian filtering and adaptive MCMC

This page was built for publication: Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-informed Deep Generative Models