Data-driven reduced order models using invariant foliations, manifolds and autoencoders

DOI10.1007/s00332-023-09932-yzbMath1525.37086arXiv2206.12269MaRDI QIDQ6168858

Robert Szalai

Publication date: 9 August 2023

Published in: Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.12269

zbMATH Keywords

invariant manifoldmachine learninginstantaneous frequencytensor approximationinvariant foliationreduced order model

Mathematics Subject Classification ID

Computational aspects of data analysis and big data (68T09) Computational methods for invariant manifolds of dynamical systems (37M21)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tensor-Train Decomposition
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• The geometry of algorithms using hierarchical tensors
• Control-based bifurcation analysis for experiments
• Extracting qualitative dynamics from experimental data
• Nonlinear prediction of chaotic time series
• Invariant manifolds associated to nonresonant spectral subspaces
• Topological properties of the set of functions generated by neural networks of fixed size
• Direct computation of nonlinear mapping via normal form for reduced-order models of finite element nonlinear structures
• A new scheme for the tensor representation
• Nonlinear normal modes and spectral submanifolds: existence, uniqueness and use in model reduction
• Diffusion maps
• Spectral properties of dynamical systems, model reduction and decompositions
• The parameterization method for invariant manifolds. III: Overview and applications
• Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
• Nonlinear System Identification
• A literature survey of low-rank tensor approximation techniques
• Projection-like Retractions on Matrix Manifolds
• Compressive Sensing and Low-Rank Libraries for Classification of Bifurcation Regimes in Nonlinear Dynamical Systems
• Hierarchical Singular Value Decomposition of Tensors
• A unified approach to attractor reconstruction
• Boundary conditions for approximate differential equations
• Nonlinear controllability and observability
• Normal Modes of Vibration for Non-Linear Continuous Systems
• The parameterization method for invariant manifolds I: Manifolds associated to non-resonant subspaces
• Trust Region Methods
• Explicit backbone curves from spectral submanifolds of forced-damped nonlinear mechanical systems
• Nonlinear model identification and spectral submanifolds for multi-degree-of-freedom mechanical vibrations
• Reconstruction of normal forms by learning informed observation geometries from data
• Appropriate initial conditions for asymptotic descriptions of the long term evolution of dynamical systems
• Deep Neural Network Approximation Theory
• Koopman Operator, Geometry, and Learning of Dynamical Systems
• An Introduction to Optimization on Smooth Manifolds
• Data-driven discovery of coordinates and governing equations
• Compressed sensing
• Foliations
• Invariant spectral foliations with applications to model order reduction and synthesis