A gradient flow on control space with rough initial condition

DOI10.1016/J.MATPUR.2025.103833MaRDI QIDQ6877803zbMATH OpenFDO

Authors Paul Gassiat, Florin Suciu

Publication date 7 January 2026

Published in Journal de Mathématiques Pures et Appliquées. Neuvième Série (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.MATPUR.2025.103833

zbMATH Keywords

gradient flowmotion planningrough pathsregularization by noise

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Control/observation systems governed by ordinary differential equations (93C15) Stochastic systems in control theory (general) (93E03) Rough paths (60L20) Regularization by noise (60H50)

Cites work

• scientific article; zbMATH DE number 3980094 (Why is no real title available?)
• scientific article; zbMATH DE number 3986319 (Why is no real title available?)
• scientific article; zbMATH DE number 4080154 (Why is no real title available?)
• scientific article; zbMATH DE number 3638903 (Why is no real title available?)
• scientific article; zbMATH DE number 1301653 (Why is no real title available?)
• scientific article; zbMATH DE number 3371284 (Why is no real title available?)
• A continuation method for motion-planning problems
• A course on rough paths. With an introduction to regularity structures
• A gradient flow equation for optimal control problems with end-point cost
• A proposal on machine learning via dynamical systems
• A tour of subriemannian geometries, their geodesics and applications
• A variation embedding theorem and applications
• Control of nonholonomic systems: from sub-Riemannian geometry to motion planning
• Control on the manifolds of mappings with a view to the deep learning
• Deep neural networks, generic universal interpolation, and controlled ODEs
• Densities for rough differential equations under Hörmander's condition
• Differential equations driven by rough signals
• Doob-Meyer for rough paths
• Exponential decay of the heat kernel over the diagonal. II
• First-order Euler scheme for SDEs driven by fractional Brownian motions: the rough case
• Large deviations and the Malliavin calculus
• Mouvement brownien et espaces de besov
• Multidimensional stochastic processes as rough paths. Theory and applications.
• On Malliavin's proof of Hörmander's theorem
• On gradients of functions definable in o-minimal structures
• Optimal convergence rate of modified Milstein scheme for SDEs with rough fractional diffusions
• Proof of the gradient conjecture of R. Thom.
• Regularity of laws and ergodicity of hypoelliptic SDEs driven by rough paths
• Scaling ResNets in the large-depth regime
• Smoothness of the density for solutions to Gaussian rough differential equations
• Stability of Deep Neural Networks via Discrete Rough Paths
• Stable architectures for deep neural networks
• Sub-Riemannian geometry and optimal transport
• The accessibility problem for geometric rough differential equations

Cited in

(1)

• Directions in rough analysis. Abstracts from the workshop held November 3--8, 2024

This page was built for publication: A gradient flow on control space with rough initial condition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6877803)