Convergence Rates and Decoupling in Linear Stochastic Approximation Algorithms
Statistics Theory
2015-01-13 v1 Statistics Theory
Abstract
Almost sure convergence rates for linear algorithms are studied, where , are symmetric, positive semidefinite random matrices and are random vectors. It is shown that a.s. for the , positive definite and vector such that and a.s. When , these assumptions are implied by the Marcinkiewicz strong law of large numbers, which allows the and to have heavy-tails, long-range dependence or both. Finally, corroborating experimental outcomes and decreasing-gain design considerations are provided.
Cite
@article{arxiv.1501.02414,
title = {Convergence Rates and Decoupling in Linear Stochastic Approximation Algorithms},
author = {Michael A. Kouritzin and Samira Sadeghi},
journal= {arXiv preprint arXiv:1501.02414},
year = {2015}
}
Comments
27 pages