Stochastic embeddings of dynamical phenomena through variational autoencoders

DOI10.1016/J.JCP.2022.110970MaRDI QIDQ2133707zbMATH OpenOpenAlexFDO

Authors Constantino A. García, Paulo Félix, Jesús M. Presedo, Abraham Otero

Publication date 5 May 2022

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

Full work available at URL https://arxiv.org/abs/2010.06265

zbMATH Keywords

Gaussian process state space modelstochastic differential equationstructured variational autoencoder

Mathematics Subject Classification ID

Nonparametric inference (62Gxx) Probabilistic methods, stochastic differential equations (65Cxx) Artificial intelligence (68Txx)

Recommendations

• Learning latent dynamics for partially observed chaotic systems
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• PI-VAE: physics-informed variational auto-encoder for stochastic differential equations
• The structure of reconstructed flows in latent spaces
• Discovery of slow variables in a class of multiscale stochastic systems via neural networks

Cites work

• A data-driven approximation of the koopman operator: extending dynamic mode decomposition
• A Stochastic Approximation Method
• A survey of numerical methods for stochastic differential equations
• A unifying view of sparse approximate Gaussian process regression
• Dynamic mode decomposition of numerical and experimental data
• Embedology
• GPflow: a Gaussian process library using TensorFlow
• Hidden physics models: machine learning of nonlinear partial differential equations
• scientific article; zbMATH DE number 6377992 (Why is no real title available?)
• scientific article; zbMATH DE number 3810550 (Why is no real title available?)
• scientific article; zbMATH DE number 469135 (Why is no real title available?)
• Learning latent dynamics for partially observed chaotic systems
• Machine learning. A probabilistic perspective
• Nonlinear Time Series Analysis
• Particle Markov Chain Monte Carlo Methods
• Practical method for determining the minimum embedding dimension of a scalar time series
• Probability for statistics and machine learning. Fundamentals and advanced topics.
• Robust Filtering and Smoothing with Gaussian Processes

Cited in

(4)

• Kernel embedding based variational approach for low-dimensional approximation of dynamical systems
• Learning nonlinear state-space models using autoencoders
• Adaptive path-integral autoencoder: representation learning and planning for dynamical systems
• Meta-state-space learning: an identification approach for stochastic dynamical systems

Describes a project that uses

Uses Software

• PMTK
• TensorFlow
• GPflow
• torchdiffeq
• torchsde
• PILCO

This page was built for publication: Stochastic embeddings of dynamical phenomena through variational autoencoders

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2133707)