Physics-Informed Probabilistic Learning of Linear Embeddings of Nonlinear Dynamics with Guaranteed Stability
From MaRDI portal
Publication:5109771
DOI10.1137/19M1267246zbMath1442.37090arXiv1906.03663MaRDI QIDQ5109771
Publication date: 13 May 2020
Published in: SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1906.03663
Bayesian inference (62F15) Time series analysis of dynamical systems (37M10) Linear composition operators (47B33) Computational methods for ergodic theory (approximation of invariant measures, computation of Lyapunov exponents, entropy, etc.) (37M25)
Related Items
Nonintrusive Reduced Order Modelling of Convective Boussinesq Flows ⋮ Structure probing neural network deflation ⋮ Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems ⋮ Model reduction for multi-scale transport problems using model-form preserving least-squares projections with variable transformation ⋮ Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling ⋮ Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network ⋮ Koopman analysis of nonlinear systems with a neural network representation ⋮ Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution ⋮ CD-ROM: complemented deep -- reduced order model ⋮ Parsimony as the ultimate regularizer for physics-informed machine learning ⋮ Parametric dynamic mode decomposition for reduced order modeling ⋮ Probabilistic-learning-based stochastic surrogate model from small incomplete datasets for nonlinear dynamical systems ⋮ Unnamed Item ⋮ Koopman operator learning using invertible neural networks ⋮ Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics ⋮ Polynomial-chaos-based conditional statistics for probabilistic learning with heterogeneous data applied to atomic collisions of helium on graphite substrate ⋮ On the structure of time-delay embedding in linear models of non-linear dynamical systems ⋮ Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics ⋮ Sparsity-promoting algorithms for the discovery of informative Koopman-invariant subspaces ⋮ Data-driven operator theoretic methods for phase space learning and analysis ⋮ Learning phase field mean curvature flows with neural networks ⋮ Two methods to approximate the Koopman operator with a reservoir computer ⋮ Deep learning models for global coordinate transformations that linearise PDEs
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- A kernel-based method for data-driven Koopman spectral analysis
- On the numerical approximation of the Perron-Frobenius and Koopman operator
- Applications of the dynamic mode decomposition
- Geometry of the ergodic quotient reveals coherent structures in flows
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- Nonlinear oscillations, dynamical systems, and bifurcations of vector fields
- A dynamic subgrid scale model for large eddy simulations based on the Mori-Zwanzig formalism
- Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
- On convergence of extended dynamic mode decomposition to the Koopman operator
- Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
- Bayesian learning for neural networks
- Linearization in the large of nonlinear systems and Koopman operator spectrum
- Variants of dynamic mode decomposition: boundary condition, Koopman, and Fourier analyses
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Spectral properties of dynamical systems, model reduction and decompositions
- On the half-Cauchy prior for a global scale parameter
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- A Computational Method to Extract Macroscopic Variables and Their Dynamics in Multiscale Systems
- On the use of Fourier averages to compute the global isochrons of (quasi)periodic dynamics
- Applied Koopmanism
- A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
- Dynamic mode decomposition of numerical and experimental data
- Spectral analysis of nonlinear flows
- Optimal prediction and the Mori–Zwanzig representation of irreversible processes
- A method for visualization of invariant sets of dynamical systems based on the ergodic partition
- A priori estimation of memory effects in reduced-order models of nonlinear systems using the Mori–Zwanzig formalism
- Data-Driven Discovery of Closure Models
- Generalizing Koopman Theory to Allow for Inputs and Control
- Ergodic Theory, Dynamic Mode Decomposition, and Computation of Spectral Properties of the Koopman Operator
- Stable architectures for deep neural networks
- Variable Projection Methods for an Optimized Dynamic Mode Decomposition
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
- Introduction to Applied Nonlinear Dynamical Systems and Chaos
- Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
- On the structure of time-delay embedding in linear models of non-linear dynamical systems
- Linearly Recurrent Autoencoder Networks for Learning Dynamics
- Probability theory. A comprehensive course
- Prior distributions for variance parameters in hierarchical models (Comment on article by Browne and Draper)
