Control of neural transport for normalising flows

DOI10.1016/J.MATPUR.2023.10.005MaRDI QIDQ6187083zbMATH OpenFDO

Authors Domènec Ruiz-Balet, Enrique Zuazua

Publication date 10 January 2024

Published in Journal de Mathématiques Pures et Appliquées. Neuvième Série (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2307.07817

zbMATH Keywords

statistical errorcouplingsneural ODEsapproximate controlnormalising flows

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Controllability (93B05) Control problems involving ordinary differential equations (34H05) Transport equations (35Q49)

Recommendations

• Neural ODE Control for Classification, Approximation, and Transport
• Normalizing flows for probabilistic modeling and inference
• Deep learning approximation of diffeomorphisms via linear-control systems
• State and observer-based feedback control of normal flow equations
• Bayesian learning via neural Schrödinger-Föllmer flows

Cites work

• A measure theoretical approach to the mean-field maximum principle for training NeurODEs
• A proposal on machine learning via dynamical systems
• Control on the manifolds of mappings with a view to the deep learning
• Deep learning approximation of diffeomorphisms via linear-control systems
• Interpolation and approximation via momentum ResNets and neural ODEs
• Large deviations
• Numerical approximation of partial differential equations
• On the rate of convergence in Wasserstein distance of the empirical measure
• Optimal Transport
• Ordinary differential equations, transport theory and Sobolev spaces
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Sparse approximation of triangular transports. I: The finite-dimensional case
• Sparse approximation of triangular transports. II: The infinite-dimensional case
• Sparsity in long-time control of neural ODEs
• The Barron space and the flow-induced function spaces for neural network models
• The Speed of Mean Glivenko-Cantelli Convergence
• Wavelet methods for pointwise regularity and local oscillations of functions

This page was built for publication: Control of neural transport for normalising flows

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6187083)