Learning the temporal evolution of multivariate densities via normalizing flows

DOI10.1063/5.0065093zbMATH Open1548.37128MaRDI QIDQ6560595

Jinqiao Duan, Felix Dietrich, Ting Gao, Yu-Bin Lu, Ioannis G. Kevrekidis, Romit Maulik

Publication date: 23 June 2024

Published in: Chaos (Search for Journal in Brave)

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Time series analysis of dynamical systems (37M10) Computational methods for ergodic theory (approximation of invariant measures, computation of Lyapunov exponents, entropy, etc.) (37M25)

Cites Work

• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• On the numerical approximation of the Perron-Frobenius and Koopman operator
• Fokker-Planck equations for stochastic dynamical systems with symmetric Lévy motions
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Data-driven model reduction and transfer operator approximation
• A data-driven approximation of the koopman operator: extending dynamic mode decomposition
• Density estimation by dual ascent of the log-likelihood
• A weak Galerkin finite element method for Burgers' equation
• Data-driven approximation of the Koopman generator: model reduction, system identification, and control
• A data-driven approach for discovering stochastic dynamical systems with non-Gaussian Lévy noise
• Generator estimation of Markov jump processes
• Dynamic mode decomposition of numerical and experimental data
• Variational estimation of the drift for stochastic differential equations from the empirical density
• Equation-free Model Reduction in Agent-based Computations: Coarse-grained Bifurcation and Variable-free Rare Event Analysis
• Lévy Processes and Stochastic Calculus
• Vector-Valued Optimal Mass Transport
• Bayesian optical flow with uncertainty quantification
• Estimating Long-Term Behavior of Flows without Trajectory Integration: The Infinitesimal Generator Approach
• A Geometric Approach to the Transport of Discontinuous Densities
• Discovering transition phenomena from data of stochastic dynamical systems with Lévy noise
• Detecting the maximum likelihood transition path from data of stochastic dynamical systems
• Data-driven discovery of coordinates and governing equations
• Analysis and Data-Based Reconstruction of Complex Nonlinear Dynamical Systems

Related Items (2)

A pseudoreversible normalizing flow for stochastic dynamical systems with various initial distributions ⋮ RandONets: shallow networks with random projections for learning linear and nonlinear operators

This page was built for publication: Learning the temporal evolution of multivariate densities via normalizing flows