An optimal control framework for adaptive neural ODEs

DOI10.1007/s10444-024-10149-0MaRDI QIDQ6561374

Joubine Aghili, O. Mula

Publication date: 25 June 2024

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

zbMATH Keywords

optimal controladaptivitydeep learningneural ODE networks

Mathematics Subject Classification ID

Computational learning theory (68Q32) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Existence theories for optimal control problems involving ordinary differential equations (49J15) Numerical solution of boundary value problems involving ordinary differential equations (65L10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal order a posteriori error estimates for a class of Runge-Kutta and Galerkin methods
• An adaptive parareal algorithm
• Error bounds for approximations with deep ReLU networks
• Deep learning as optimal control problems: models and numerical methods
• A mean-field optimal control formulation of deep learning
• A proposal on machine learning via dynamical systems
• On shooting methods for boundary value problems
• Résolution d'EDP par un schéma en temps «pararéel »
• Remarks on Inequalities for Large Deviation Probabilities
• Method of successive approximations for solution of optimal control problems
• Stable architectures for deep neural networks
• Layer-Parallel Training of Deep Residual Neural Networks
• Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs
• Error bounds for approximations with deep ReLU neural networks in Ws,p norms
• Neural ODE Control for Classification, Approximation, and Transport
• Deep learning via dynamical systems: an approximation perspective

This page was built for publication: An optimal control framework for adaptive neural ODEs