ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

q-Gaussian based Smoothed Functional Algorithms for Stochastic Optimization

Ghoshdastidar, Debarghya and Dukkipati, Ambedkar and Bhatnagar, Shalabh (2012) q-Gaussian based Smoothed Functional Algorithms for Stochastic Optimization. In: IEEE International Symposium on Information Theory, JUL 01-06, 2012 , Cambridge, MA .

[img] PDF
ieee_int_sym_inf_the_pro-2012.pdf - Published Version
Restricted to Registered users only

Download (210kB) | Request a copy
Official URL: http://dx.doi.org/10.1109/ISIT.2012.6283013

Abstract

The q-Gaussian distribution results from maximizing certain generalizations of Shannon entropy under some constraints. The importance of q-Gaussian distributions stems from the fact that they exhibit power-law behavior, and also generalize Gaussian distributions. In this paper, we propose a Smoothed Functional (SF) scheme for gradient estimation using q-Gaussian distribution, and also propose an algorithm for optimization based on the above scheme. Convergence results of the algorithm are presented. Performance of the proposed algorithm is shown by simulation results on a queuing model.

Item Type: Conference Paper
Series.: IEEE International Symposium on Information Theory
Publisher: IEEE
Additional Information: Copyright for this article belongs to IEEE, NEW YORK
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Date Deposited: 07 Feb 2013 11:50
Last Modified: 07 Feb 2013 11:50
URI: http://eprints.iisc.ac.in/id/eprint/45752

Actions (login required)

View Item View Item