Sufficient and necessary condition for the convergence of stochastic approximation algorithms

DOI10.1016/j.spl.2005.07.020zbMath1093.62079OpenAlexW2033836085WikidataQ62862130 ScholiaQ62862130MaRDI QIDQ2489838

Wen-bin Liu, Jian-Feng Feng, Nei-Ping Chen

Publication date: 28 April 2006

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.spl.2005.07.020

zbMATH Keywords

stochastic optimizationstochastic differential equationssimulated annealingnonlinear dynamicslocal minimastochastic algorithmsglobal minima

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Applications of stochastic analysis (to PDEs, etc.) (60H30) Stochastic approximation (62L20) Ordinary differential equations and systems with randomness (34F05) Generation, random and stochastic difference and differential equations (37H10)

Related Items

Stochastic approximation results for variational inequality problem using random-type iterative schemes, Stochastic protein folding simulation in the three-dimensional HP-model

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Large-time behavior of perturbed diffusion Markov processes with applications to the second eigenvalue problem for Fokker-Planck operators and simulated annealing
• Rough large deviation estimates for simulated annealing: Application to exponential schedules
• Stochastic approximation methods for constrained and unconstrained systems
• Cooling Schedules for Optimal Annealing
• On the Convergence Rate of Annealing Processes
• Asymptotically optimal rate of convergence of smoothed stochastic recursive algorithms
• A Stochastic Approximation Method