Concentration Bounds for Stochastic Approximations

Abstract : We obtain non asymptotic concentration bounds for two kinds of stochastic approximations. We first consider the deviations between the expectation of a given function of the Euler scheme of some diffusion process at a fixed deterministic time and its empirical mean obtained by the Monte-Carlo procedure. We then give some estimates concerning the deviation between the value at a given time-step of a stochastic approximation algorithm and its target. Under suitable assumptions both concentration bounds turn out to be Gaussian. The key tool consists in exploiting accurately the concentration properties of the increments of the schemes. For the first case, as opposed to the previous work of Lemaire and Menozzi (EJP, 2010), we do not have any systematic bias in our estimates. Also, no specific non-degeneracy conditions are assumed.
Document type :
Journal articles
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00688165
Contributor : Stephane Menozzi <>
Submitted on : Monday, December 10, 2012 - 2:36:10 PM
Last modification on : Sunday, March 31, 2019 - 1:32:38 AM
Long-term archiving on : Monday, March 11, 2013 - 12:30:38 PM

Files

47.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00688165, version 3
  • ARXIV : 1204.3730

Citation

Noufel Frikha, Stephane Menozzi. Concentration Bounds for Stochastic Approximations. Electronic Communications in Probability, Institute of Mathematical Statistics (IMS), 2012, 17 (47), 15p. ⟨https://projecteuclid.org/euclid.ecp/1465263180⟩. ⟨hal-00688165v3⟩

Share

Metrics

Record views

410

Files downloads

204