Cluster-based classification with neural ODEs via control

DOI10.4208/JML.241114MaRDI QIDQ6955696zbMATH OpenFDO

Authors Antonio Álvarez-López, Rafael Orive, Enrique Zuazua

Publication date 22 July 2025

Published in Journal of Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.4208/JML.241114

zbMATH Keywords

classificationcomplexitycontrollabilityseparabilityneural ODEs

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07) Controllability (93B05) Nonlinear ordinary differential equations and systems (34A34) Control/observation systems governed by ordinary differential equations (93C15)

Cites work

• 10.1162/153244303322533223
• A mathematical framework for learning probability distributions
• A mean-field optimal control formulation of deep learning
• A measure theoretical approach to the mean-field maximum principle for training NeurODEs
• A proposal on machine learning via dynamical systems
• Algorithms for weak and wide separation of sets
• Benign overfitting in linear regression
• Control of neural transport for normalising flows
• Deep learning via dynamical systems: an approximation perspective
• Deep neural networks, generic universal interpolation, and controlled ODEs
• Enumeration of Seven-Argument Threshold Functions
• Geometric Invariant Theory
• Interpolation and approximation via momentum ResNets and neural ODEs
• Interpolation, approximation, and controllability of deep neural networks
• Maximum principle based algorithms for deep learning
• Neural ODE Control for Classification, Approximation, and Transport
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Random forests
• SOME LOWER BOUNDS ON GEOMETRIC SEPARABILITY PROBLEMS
• Separating collections of points in Euclidean spaces
• Shattering All Sets of ‘k’ Points in “General Position” Requires (k — 1)/2 Parameters
• Sparsity in long-time control of neural ODEs
• Stable architectures for deep neural networks
• Support-vector networks
• The Number of Linearly Inducible Orderings of Points in d-Space
• Turnpike in optimal control of PDEs, ResNets, and beyond
• Universal Approximation Power of Deep Residual Neural Networks Through the Lens of Control
• Variational formulations of ODE-Net as a mean-field optimal control problem and existence results

This page was built for publication: Cluster-based classification with neural ODEs via control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6955696)