An optimal control framework for adaptive neural ODEs

DOI10.1007/S10444-024-10149-0MaRDI QIDQ6561374FDOQ6561374

Authors: Joubine Aghili, O. Mula 

Publication date: 25 June 2024

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

Recommendations

• Deep learning as optimal control problems: models and numerical methods
• Neural ODE Control for Classification, Approximation, and Transport
• Sparsity in long-time control of neural ODEs
• A measure theoretical approach to the mean-field maximum principle for training NeurODEs
• Neural ODEs as the deep limit of ResNets with constant weights

zbMATH Keywords

deep learningoptimal controladaptivityneural ODE networks

Mathematics Subject Classification ID

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

Cites Work

• Title not available (Why is that?)
• Remarks on Inequalities for Large Deviation Probabilities
• A ``parareal in time discretization of PDE's
• Introduction to the mathematical theory of control
• Optimal order a posteriori error estimates for a class of Runge-Kutta and Galerkin methods
• Method of successive approximations for solution of optimal control problems
• The maximum principle in optimal control, then and now
• On shooting methods for boundary value problems
• Error bounds for approximations with deep ReLU networks
• A mean-field optimal control formulation of deep learning
• Stable architectures for deep neural networks
• A proposal on machine learning via dynamical systems
• Maximum principle based algorithms for deep learning
• Deep learning as optimal control problems: models and numerical methods
• Neural architecture search: a survey
• Layer-Parallel Training of Deep Residual Neural Networks
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
• An adaptive parareal algorithm
• Deep learning via dynamical systems: an approximation perspective
• Deep neural networks, generic universal interpolation, and controlled ODEs
• Neural ODE Control for Classification, Approximation, and Transport

Cited In (3)

• Sparsity in long-time control of neural ODEs
• Enhancing continuous time series modelling with a latent ODE-LSTM approach
• Implementation and (inverse modified) error analysis for implicitly templated ODE-nets

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6561374)