Deep learning approximation of diffeomorphisms via linear-control systems

DOI10.3934/MCRF.2022036zbMath1516.49032arXiv2110.12393OpenAlexW3209861131MaRDI QIDQ6099195

A. Scagliotti

Publication date: 19 June 2023

Published in: Mathematical Control and Related Fields (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.12393

zbMATH Keywords

gradient flowPontryagin maximum principledeep learning\( \Gamma \)-convergencelinear-control system

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Methods involving semicontinuity and convergence; relaxation (49J45) Existence theories for optimal control problems involving ordinary differential equations (49J15) Discrete approximations in optimal control (49M25) Linear optimal control problems (49N05)

Related Items (2)

Optimal control of ensembles of dynamical systems ⋮ Control of neural transport for normalising flows

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An introduction to \(\Gamma\)-convergence
• Mean-field Pontryagin maximum principle
• Control theory from the geometric viewpoint.
• Deep learning as optimal control problems: models and numerical methods
• A proposal on machine learning via dynamical systems
• Optimal control of distributions
• Ensemble controllability by Lie algebraic methods
• Probability and Stochastics
• Control in the Spaces of Ensembles of Points
• Method of successive approximations for solution of optimal control problems
• On global convergence of an algorithm for optimal control
• Stable architectures for deep neural networks
• A Comprehensive Introduction to Sub-Riemannian Geometry

This page was built for publication: Deep learning approximation of diffeomorphisms via linear-control systems