ICAR Research Data Repository for Knowledge Management
Stochastic approximation with long range dependent and heavy tailed noise
DSpace at IIT Bombay
View Archive Info| Field | Value | |
| Title |
Stochastic approximation with long range dependent and heavy tailed noise
|
|
| Creator |
ANANTHARAM, V
BORKAR, VS |
|
| Subject |
Stochastic approximation
Long range dependence Heavy tailed noise O.d.e. limit Convergence in xi th mean |
|
| Description |
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.
|
|
| Publisher |
SPRINGER
|
|
| Date |
2014-10-17T05:39:58Z
2014-10-17T05:39:58Z 2012 |
|
| Type |
Article
|
|
| Identifier |
QUEUEING SYSTEMS, 71(1-2)221-242
http://dx.doi.org/10.1007/s11134-012-9283-0 http://dspace.library.iitb.ac.in/jspui/handle/100/16090 |
|
| Language |
en
|
|