The Annals of Applied Probability
- Ann. Appl. Probab.
- Volume 26, Number 2 (2016), 933-985.
Multi-level stochastic approximation algorithms
This paper studies multi-level stochastic approximation algorithms. Our aim is to extend the scope of the multi-level Monte Carlo method recently introduced by Giles [Oper. Res. 56 (2008) 607–617] to the framework of stochastic optimization by means of stochastic approximation algorithm. We first introduce and study a two-level method, also referred as statistical Romberg stochastic approximation algorithm. Then its extension to a multi-level method is proposed. We prove a central limit theorem for both methods and give optimal parameters. Numerical results confirm the theoretical analysis and show a significant reduction in the initial computational cost.
Ann. Appl. Probab., Volume 26, Number 2 (2016), 933-985.
Received: October 2013
Revised: February 2015
First available in Project Euclid: 22 March 2016
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Frikha, Noufel. Multi-level stochastic approximation algorithms. Ann. Appl. Probab. 26 (2016), no. 2, 933--985. doi:10.1214/15-AAP1109. https://projecteuclid.org/euclid.aoap/1458651825