Control of neural transport for normalising flows

DOI10.1016/J.MATPUR.2023.10.005zbMath1530.35247arXiv2307.07817MaRDI QIDQ6187083

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

couplingsstatistical errorneural 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)

Cites Work

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

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