Stochastic approximation algorithms: overview and recent trends.

DOI10.1007/BF02823149zbMath1075.62608MaRDI QIDQ5955825

Vivek S. Borkar, B. Bharath

Publication date: 18 February 2002

Published in: Sādhanā (Search for Journal in Brave)

Mathematics Subject Classification ID

62L20: Stochastic approximation

Related Items

Two Timescale Analysis of the Alopex Algorithm for Optimization, Learning automata algorithms for pattern classification., Annealing stochastic approximation Monte Carlo algorithm for neural network training

Cites Work

• Passive stochastic approximation with constant step size and window width
• A Dynamical System Approach to Stochastic Approximations
• An alternative proof for convergence of stochastic approximation algorithms
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization
• Equation of State Calculations by Fast Computing Machines
• Multiscale Stochastic Approximation for Parametric Optimization of Hidden Markov Models
• Smoothing Derivatives of Functions and Applications
• Stochastic Estimation of the Maximum of a Regression Function
• A Stochastic Approximation Method
• A tutorial survey of reinforcement learning
• Learning automata algorithms for pattern classification.
• Some results characterizing the finite time behaviour of the simulated annealing algorithm.
• Structure theorems for partially asynchronous iterations of a nonnegative matrix with random delays.
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Markov chains and stochastic stability
• Nonconvergence to unstable points in urn models and stochastic approximations
• Infinitesimal and finite perturbation analysis for queueing networks
• A Newton-Raphson version of the multivariate Robbins-Monro procedure
• Large deviations analysis of some recursive algorithms with state dependent noise
• Distributed computation of fixed points of \(\infty\)-nonexpansive maps
• New method of stochastic approximation type
• Identification and stochastic adaptive control
• Ordinal optimization of DEDS
• Transformation of observations in stochastic approximation
• Stochastic approximation methods for constrained and unconstrained systems
• Strong convergence of a stochastic approximation algorithm
• A strong approximation theorem for stochastic recursive algorithms
• Learning mixed equilibria
• Asynchronous stochastic approximation and Q-learning
• Convergence of solutions to equations arising in neural networks
• Learning through reinforcement and replicator dynamics
• Weak convergence of recursions
• Stochastic approximation with two time scales
• On optimal estimation methods using stochastic approximation procedures
• On the almost sure asymptotic behaviour of stochastic algorithm
• \({\mathcal Q}\)-learning
• Continuous action set learning automata for stochastic optimization
• Learning dynamics in games with stochastic perturbations
• Do stochastic algorithms avoid traps?
• Pseudogradient adaptation and training algorithms
• Random optimization
• Adaption and learning in automatic systems. Translated by Z. J. Nikolic
• Chaotic relaxation
• Convergence of a class of random search algorithms
• Passive stochastic approximation
• A LEARNING ALGORITHM FOR DISCRETE-TIME STOCHASTIC CONTROL
• A stochastic method for global optimization
• Recursive self-tuning control of finite Markov chains
• Stochastic approximation method with gradient averaging for unconstrained problems
• A generalized URN problem and its applications
• Stochastic Approximations via Large Deviations: Asymptotic Properties
• Stochastic Minimization with Constant Step-Size: Asymptotic Laws
• Distributed asynchronous deterministic and stochastic gradient optimization algorithms
• Learning Optimal Discriminant Functions through a Cooperative Game of Automata
• Smoothed (conditional) perturbation analysis of discrete event dynamical systems
• Nonparametric sequential estimation of zeros and extrema of regression functions
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• Extensions of infinitesimal perturbation analysis
• Stochastic approximation algorithms for parallel and distributed processing
• Gradient approach for recursive estimation and control in finite Markov chains
• A fundamental approach to the convergence analysis of least squares algorithms
• Minimization by Random Search Techniques
• Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $
• On extensions of Polyak's averaging approach to stochastic approximation
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Acceleration of Stochastic Approximation by Averaging
• On positive real transfer functions and the convergence of some recursive schemes
• Analysis of recursive stochastic algorithms
• Some Pathological Traps for Stochastic Approximation
• Recursive algorithms, urn processes and chaining number of chain recurrent sets
• Stochastic optimization of regenerative systems using infinitesimal perturbation analysis
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• An analysis of temporal-difference learning with function approximation
• Stochastic differential equations: singularity of coefficients, regression models, and stochastic approximation
• Weighted Means in Stochastic Approximation of Minima
• Annealing of Iterative Stochastic Schemes
• Convergence Rate of Stochastic Approximation Algorithms in the Degenerate Case
• Asynchronous Stochastic Approximations
• The dynamic system method and the traps
• Two Timescale Analysis of the Alopex Algorithm for Optimization
• Gradient Convergence in Gradient methods with Errors
• Stochastic approximation with random truncations, state-dependent noise and discontinuous dynamics
• Convergence of sa algorithms in multi-root or multi-extreme cases
• Simulation-based optimization of Markov reward processes
• Equivalent necessary and sufficient conditions on noise sequences for stochastic approximation algorithms
• General results on the convergence of stochastic algorithms
• Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence
• Stochastic approximation with averaging and feedback: rapidly convergent "on-line" algorithms
• Asymptotically optimal rate of convergence of smoothed stochastic recursive algorithms
• Probability metrics and recursive algorithms