Newton-based stochastic optimization using q-Gaussian smoothed functional algorithms
From MaRDI portal
Publication:472587
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 et al., 2013), we presented gradient SF algorithms based on the q-Gaussian perturbations. Our work extends prior work on smoothed functional algorithms by generalizing the class of perturbation distributions as most distributions reported in the literature for which SF algorithms are known to work and 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 several 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 (Bhatnagar, 2007) and Cauchy perturbations, as well as the gradient q-Gaussian SF algorithms (Ghoshdastidar et al., 2013).
Recommendations
- Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization
- Adaptive Newton-based multivariate smoothed functional algorithms for simulation optimization
- Smoothed functional algorithms for stochastic optimization using \(q\)-Gaussian distributions
- scientific article; zbMATH DE number 4185529
- Simultaneous perturbation Newton algorithms for simulation optimization
Cites work
- scientific article; zbMATH DE number 3841285 (Why is no real title available?)
- scientific article; zbMATH DE number 5348356 (Why is no real title available?)
- scientific article; zbMATH DE number 1321699 (Why is no real title available?)
- scientific article; zbMATH DE number 700091 (Why is no real title available?)
- A Newton-Raphson version of the multivariate Robbins-Monro procedure
- A Stochastic Approximation Method
- A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization
- Adaptive Newton-based multivariate smoothed functional algorithms for simulation optimization
- Adaptive stochastic approximation by the simultaneous perturbation method
- Convergence of a class of random search algorithms
- Estimation of the derivative of a stationary measure with respect to a control parameter
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms
- Nondifferentiable optimization via smooth approximation: General analytical approach
- Smoothed functional algorithms for stochastic optimization using \(q\)-Gaussian distributions
- Stochastic Estimation of the Maximum of a Regression Function
- Stochastic approximation methods for constrained and unconstrained systems
- Stochastic recursive algorithms for optimization. Simultaneous perturbation methods
Cited in
(6)- Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms
- Projection theorems and estimating equations for power-law models
- Adaptive Newton-based multivariate smoothed functional algorithms for simulation optimization
- Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization
- Truncated Cauchy random perturbations for smoothed functional-based stochastic optimization
- Smoothed functional algorithms for stochastic optimization using \(q\)-Gaussian distributions
This page was built for publication: Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q472587)
