Wear convergence rates for stochastic approximation with application to multiple targets and simulated annealing

• 成果类型: Article
• 署名作者: Pelletier, M
• 署名单位: Universite Gustave-Eiffel
• 刊物名称: ANNALS OF APPLIED PROBABILITY
• ISSN/ISSBN: 1050-5164
• 发表日期: 1998
• 页码: 10-44
• 关键词: global optimization; 2nd eigenvalue; algorithms; diffusion; BEHAVIOR; bounds; RD

摘要

We study convergence rates of R-d-valued algorithms, especially in the case of multiple targets and simulated annealing. We precise, for example, the convergence rate of simulated annealing algorithms, whose weak convergence to a distribution concentrated on the potential's minima had been established by Gelfand and Mitter or by Hwang and Sheu.