On the convergence of global-optimization fraudulent stochastic algorithms

DOI10.5802/AHL.242MaRDI QIDQ6886753zbMATH OpenFDO

Authors Laurent Miclo

Publication date 10 December 2025

Published in Annales Henri Lebesgue (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.5802/AHL.242

zbMATH Keywords

almost sure convergenceBessel processesdiffusion processesglobal optimizationMorse functionsRiemannian manifoldsstochastic algorithms

Mathematics Subject Classification ID

Diffusion processes and stochastic analysis on manifolds (58J65) Strong limit theorems (60F15) Diffusion processes (60J60) Nonconvex programming, global optimization (90C26) Optimal stochastic control (93E20)

Cites work

• Asymptotics of the spectral gap with applications to the theory of simulated annealing
• Bessel processes, the Brownian snake and super-Brownian motion
• Hamilton's Ricci flow
• scientific article; zbMATH DE number 3951715 (Why is no real title available?)
• scientific article; zbMATH DE number 43057 (Why is no real title available?)
• scientific article; zbMATH DE number 1245556 (Why is no real title available?)
• scientific article; zbMATH DE number 4001209 (Why is no real title available?)
• Multidimensional diffusion processes.
• Stochastic gradient descent with noise of machine learning type. II: Continuous time analysis
• Stochastic modified equations and dynamics of stochastic gradient algorithms. I: Mathematical foundations
• Swarm gradient dynamics for global optimization: the mean-field limit case

Cited in

(1)

• The asymptotic behavior of fraudulent algorithms

This page was built for publication: On the convergence of global-optimization fraudulent stochastic algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6886753)