Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
Author:
- Mariane PelletierMPMariane Pelletier
Open Access
- 1 February 1998
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Applied Probability
- Vol. 8 (1) , 10-44
Abstract
We study convergence rates of $\mathbb{R}$-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.Keywords
This publication has 26 references indexed in Scilit:
- Convergence rates for annealing diffusion processesThe Annals of Applied Probability, 1997
- Convergence of stochastic algorithms: from the Kushner–Clark theorem to the Lyapounov functional methodAdvances in Applied Probability, 1996
- Non-standard limit theorems for urn models and stochastic approximation proceduresCommunications in Statistics. Stochastic Models, 1995
- Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processesAdvances in Applied Probability, 1993
- Large-time behavior of perturbed diffusion markov processes with applications to the second eigenvalue problem for fokker-planck operators and simulated annealingActa Applicandae Mathematicae, 1990
- Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying boundsStochastic Processes and their Applications, 1987
- Stable convergence of semimartingalesStochastic Processes and their Applications, 1985
- Laplace's Method Revisited: Weak Convergence of Probability MeasuresThe Annals of Probability, 1980
- A Weak Convergence Theorem with Application to the Robbins-Monro ProcessThe Annals of Probability, 1978
- Stochastic Estimation of the Maximum of a Regression FunctionThe Annals of Mathematical Statistics, 1952