Convergence error analysis of reflected gradient Langevin dynamics for non-convex constrained optimization

DOI10.1007/s13160-024-00667-1MaRDI QIDQ6671887

Reiichiro Kawai, Taiji Suzuki, Kanji Sato, Akiko Takeda

Publication date: 27 January 2025

Published in: Japan Journal of Industrial and Applied Mathematics (Search for Journal in Brave)

zbMATH Keywords

reflected diffusionnon-asymptotic analysisgradient Langevin dynamicsnon-convex constrained optimization problemRademacher noise

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Diffusion processes (60J60) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31)

This page was built for publication: Convergence error analysis of reflected gradient Langevin dynamics for non-convex constrained optimization