Title :
Stochastic approximation with ‘bad’ noise
Author :
Anantharam, Venkat ; Borkar, Vivek S.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of California, Berkeley, CA, USA
Abstract :
Stability and convergence properties of stochastic approximation algorithms are analyzed when the noise includes a long range dependent component (modeled by a fractional Brownian motion) and a heavy tailed component (modeled by a symmetric stable process), in addition to the usual `martingale noise´. This is motivated by the emergent applications in communications. The proofs are based on comparing suitably interpolated iterates with a limiting ordinary differential equation. Related issues such as asynchronous implementations, Markov noise, etc. are briefly discussed.
Keywords :
Brownian motion; Markov processes; differential equations; interference (signal); noise; stochastic processes; Markov noise; fractional Brownian motion; interpolated iterates; ordinary differential equation; stochastic approximation; Approximation methods; Asymptotic stability; Brownian motion; Convergence; Markov processes; Noise;
Conference_Titel :
Information Theory and Applications Workshop (ITA), 2011
Conference_Location :
La Jolla, CA
Print_ISBN :
978-1-4577-0360-7
Electronic_ISBN :
978-1-4577-0361-4
DOI :
10.1109/ITA.2011.5743559
