Adaptive stochastic approximation algorithm
From MaRDI portal
The authors propose a new adaptive step size scheme for the stochastic approximation algorithms based on the tracking of previously noisy function values. Numerical expriments verify better performance of the proposed algorithm with adaptive step sizes compared to the existing algorithms.
Recommendations
- Stochastic approximation with adaptive step sizes for optimization in noisy environment and its application in regression models
- Descent direction stochastic approximation algorithm with adaptive step sizes
- Stabilization of stochastic approximation by step size adaptation
- New stochastic approximation algorithms with adaptive step sizes
- Analysis of adaptive step-size SA algorithms for parameter tracking
Cites work
- A combined direction stochastic approximation algorithm
- A gradient method for unconstrained optimization in noisy environment
- A new hybrid stochastic approximation algorithm
- A stochastic approximation frame algorithm with adaptive directions
- A Stochastic Approximation Method
- A stochastic quasi-Newton method for large-scale optimization
- Accelerated Stochastic Approximation
- Accelerated Stochastic Approximation
- Adaptive stochastic approximation by the simultaneous perturbation method
- Approximate Dynamic Programming
- Descent direction method with line search for unconstrained optimization in noisy environment
- Gradient Convergence in Gradient methods with Errors
- scientific article; zbMATH DE number 48363 (Why is no real title available?)
- scientific article; zbMATH DE number 1391242 (Why is no real title available?)
- Introduction to Stochastic Search and Optimization
- New stochastic approximation algorithms with adaptive step sizes
- On stochastic gradient and subgradient methods with adaptive steplength sequences
- On the use of stochastic Hessian information in optimization methods for machine learning
- Sample size selection in optimization methods for machine learning
- Stochastic approximation and its applications
- Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
- Testing Unconstrained Optimization Software
- The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem
Cited in
(31)- Stationary adaptive search strategy as an alternative to the method of stochastic approximation
- A stochastic approximation algorithm with step-size adaptation
- Strong representation of an adaptive stochastic approximation procedure
- New stochastic approximation algorithms with adaptive step sizes
- Rates of convergence of adaptive step-size of stochastic approximation algorithms
- Adaptive stepsize selection for tracking in a regime-switching environment
- Linear stochastic approximation driven by slowly varying Markov chains
- A randomized stochastic approximation algorithm for self-learning
- Adaptive stochastic approximation by the simultaneous perturbation method
- Efficiency of the stochastic approximation method
- New combinatorial direction stochastic approximation algorithms
- A scaled stochastic approximation algorithm for antenna arrays adaptive filtering problems
- Stochastic approximation with adaptive step sizes for optimization in noisy environment and its application in regression models
- A self-adaptive and variable stepwise ALOPEX algorithm
- A stochastic approximation frame algorithm with adaptive directions
- Application of stochastic approximation in technical design
- scientific article; zbMATH DE number 4099037 (Why is no real title available?)
- scientific article; zbMATH DE number 53162 (Why is no real title available?)
- On stochastic gradient and subgradient methods with adaptive steplength sequences
- Stabilization of stochastic approximation by step size adaptation
- scientific article; zbMATH DE number 778105 (Why is no real title available?)
- Analysis of adaptive step-size SA algorithms for parameter tracking
- Multidimensional stochastic approximation
- Descent direction stochastic approximation algorithm with adaptive step sizes
- Adaptive System Optimization Using Random Directions Stochastic Approximation
- scientific article; zbMATH DE number 970352 (Why is no real title available?)
- Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning
- A stochastic approximation algorithm with multiplicative step size modification
- On adaptive and non-adaptive stochastic and deterministic algorithms
- A combined direction stochastic approximation algorithm
- Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming
This page was built for publication: Adaptive stochastic approximation algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1689446)
