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

Newton-based stochastic optimization using q-Gaussian smoothed functional algorithms

Ghoshdastidar, Debarghya and Dukkipati, Ambedkar and Bhatnagar, Shalabh (2014) Newton-based stochastic optimization using q-Gaussian smoothed functional algorithms. In: AUTOMATICA, 50 (10). pp. 2606-2614.

[img] PDF
aut_50-10_2606_2014.pdf - Published Version
Restricted to Registered users only

Download (568kB) | Request a copy
Official URL: http://dx.doi.org/ 10.1016/j.automatica.2014.08.02...

Abstract

We present the first q-Gaussian smoothed functional (SF) estimator of the Hessian and the first Newton-based stochastic optimization algorithm that estimates both the Hessian and the gradient of the objective function using q-Gaussian perturbations. Our algorithm requires only two system simulations (regardless of the parameter dimension) and estimates both the gradient and the Hessian at each update epoch using these. We also present a proof of convergence of the proposed algorithm. In a related recent work (Ghoshdastidar, Dukkipati, & Bhatnagar, 2014), we presented gradient SF algorithms based on the q-Gaussian perturbations. Our work extends prior work on SF algorithms by generalizing the class of perturbation distributions as most distributions reported in the literature for which SF algorithms are known to work turn out to be special cases of the q-Gaussian distribution. Besides studying the convergence properties of our algorithm analytically, we also show the results of numerical simulations on a model of a queuing network, that illustrate the significance of the proposed method. In particular, we observe that our algorithm performs better in most cases, over a wide range of q-values, in comparison to Newton SF algorithms with the Gaussian and Cauchy perturbations, as well as the gradient q-Gaussian SF algorithms. (C) 2014 Elsevier Ltd. All rights reserved.

Item Type: Journal Article
Publication: AUTOMATICA
Additional Information: Copyright for this articles belongs to the PERGAMON-ELSEVIER SCIENCE LTD, THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Date Deposited: 14 Dec 2014 10:55
Last Modified: 14 Dec 2014 10:55
URI: http://eprints.iisc.ac.in/id/eprint/50446

Actions (login required)

View Item View Item