Smoothed Functional Algorithms for Stochastic Optimization Using q -Gaussian Distributions
From MaRDI portal
Publication:5270716
DOI10.1145/2628434zbMath1369.90111arXiv1206.4832OpenAlexW2076037361MaRDI QIDQ5270716
Ambedkar Dukkipati, Debarghya Ghoshdastidar, Shalabh Bhatnagar
Publication date: 30 June 2017
Published in: ACM Transactions on Modeling and Computer Simulation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1206.4832
\(q\)-Gaussiantwo-timescale stochastic approximationsmoothed functional algorithmsprojected gradient-based search
Related Items (2)
Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms ⋮ A Monte Carlo multi-asset option pricing approximation for general stochastic processes
Cites Work
- Unnamed Item
- Unnamed Item
- Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms
- Stochastic approximation. A dynamical systems viewpoint.
- A Newton-Raphson version of the multivariate Robbins-Monro procedure
- Nondifferentiable optimization via smooth approximation: General analytical approach
- Stochastic approximation methods for constrained and unconstrained systems
- Possible generalization of Boltzmann-Gibbs statistics.
- Convergence of a class of random search algorithms
- Adaptive stochastic approximation by the simultaneous perturbation method
- Law of Error in Tsallis Statistics
- Generalized Box–MÜller Method for Generating $q$-Gaussian Random Deviates
- Smoothed Functionals and Constrained Stochastic Approximation
- Probability with Martingales
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Estimation of the derivative of a stationary measure with respect to a control parameter
- Some Pathological Traps for Stochastic Approximation
- A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization
- Central limit theorem and deformed exponentials
- Perturbation theory and finite Markov chains
- Stochastic Estimation of the Maximum of a Regression Function
- A Stochastic Approximation Method
This page was built for publication: Smoothed Functional Algorithms for Stochastic Optimization Using q -Gaussian Distributions
