Stochastic approximation algorithms and applications
From MaRDI portal
This book is concerned with the qualitative and asymptotic properties of stochastic approximation algorithms in many diverse forms in which they arise in applications. The first three chapters deal with the classical Robbins-Monro and Kiefer-Wolfowitz methods and their modifications motivated by practical considerations. Many examples of applications to learning, state dependent noise, queueing as well as in signal processing and adaptive control are described. The five following chapters give the mathematical background concerning the convergence theorems of the algorithms (convergence in probability as well as weak convergence). The proofs of convergence and investigation of the rate of convergence of the applications mentioned before follow. The problem of selecting a good step size sequence for the algorithms is dealt with in the last but one chapter. The closing chapter concerns the decentralized and asynchronous forms of the stochastic approximation algorithms.
Recommendations
Cited in
(only showing first 100 items - show all)- A new continuous action-set learning automaton for function optimization
- Natural actor-critic algorithms
- Abstract stochastic approximations and applications
- Improved results on the robustness of stochastic approximation algorithms
- Sequential credibility evaluation for symmetric location claim distributions
- Constrained stochastic estimation algorithms for a class of hybrid stock market models
- Probabilistic design of LPV control systems.
- Stochastic algorithms: Foundations and applications. Second international symposium, SAGA 2003, Hatfield, UK, September 22--23, 2003. Proceedings
- Accelerated randomized stochastic optimization.
- Vertex-reinforced random walk on \(\mathbb Z\) has finite range
- A class of learning/estimation algorithms using nominal values: Asymptotic analysis and applications
- Deterministic convergence of an online gradient method for neural networks
- Privacy preserving distributed optimization using homomorphic encryption
- Synchronization and functional central limit theorems for interacting reinforced random walks
- Estimation of an optimal solution of a LP problem with unknown objective function
- Adaptive designs and Robbins-Monro algorithm
- Randomized algorithms for stochastic approximation under arbitrary disturbances
- On the convergence of reinforcement learning
- Real-time reinforcement learning by sequential actor-critics and experience replay
- Convergence of a stochastic approximation version of the EM algorithm
- Recursive estimation of a drifted autoregressive parameter.
- Stochastic approximation and its applications
- Workshop on statistical approaches for the evaluation of complex computer models
- Generalized neural networks for spectral analysis: dynamics and Liapunov functions
- Convergence rate of linear two-time-scale stochastic approximation.
- Analysis of a high-resolution optical wave-front control system
- Perturbation analysis for production control and optimization of manufacturing systems
- Stochastic algorithms
- New stochastic approximation algorithms with adaptive step sizes
- Stochastic Nelder-Mead simplex method -- a new globally convergent direct search method for simulation optimization
- Error bounds for constant step-size \(Q\)-learning
- Approximate stochastic annealing for online control of infinite horizon Markov decision processes
- Long range search for maximum likelihood in exponential families
- Online expectation maximization based algorithms for inference in hidden Markov models
- Recursive estimation procedures for one-dimensional parameter of statistical models associated with semimartingales
- Convergence of stochastic proximal gradient algorithm
- Structural stability threshold for the condition of robust no deterministic sure arbitrage with unbounded profit
- Fundamental design principles for reinforcement learning algorithms
- Large deviations and stochastic stability in population games
- Reference points and learning
- ASD+M: automatic parameter tuning in stochastic optimization and on-line learning
- \(\alpha\)-variational inference with statistical guarantees
- Semimartingale stochastic approximation procedure and recursive estimation
- Simultaneous perturbation Newton algorithms for simulation optimization
- A latent discrete Markov random field approach to identifying and classifying historical forest communities based on spatial multivariate tree species counts
- On the stability of an adaptive learning dynamics in traffic games
- Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents
- Convergence of the Robbins-Monro process with small steps from below
- Equilibrium routing under uncertainty
- A survey of randomized algorithms for control synthesis and performance verification
- An information-theoretic analysis of return maximization in reinforcement learning
- Quantile estimation with adaptive importance sampling
- Online calibrated forecasts: memory efficiency versus universality for learning in games
- Stochastic approximation with series of delayed observations
- Scaling up Bayesian variational inference using distributed computing clusters
- A sequential design for a clinical trial with a linear prognostic factor
- Transient and asymptotic dynamics of reinforcement learning in games
- Dynamic modeling and control of supply chain systems: A review
- Equilibrium selection in games: the mollifier method
- Bayesian and non-Bayesian analysis of gamma stochastic frontier models by Markov chain Monte Carlo methods
- The asymptotic equipartition property in reinforcement learning and its relation to return maximization
- Design and analysis of linear precoders under a mean square error criterion. II: MMSE designs and conclusions
- An ellipsoid algorithm for probabilistic robust controller design
- Linear stochastic approximation driven by slowly varying Markov chains
- A dual purpose principal and minor component flow
- A law of the iterated logarithm for stochastic approximation procedures in d-dimensional Euclidean space.
- Learning aspiration in repeated games
- Tuning positive feedback for signal detection in noisy dynamic environments
- A distributed methodology for approximate uniform global minimum sharing
- Importance sampling and statistical Romberg method for Lévy processes
- Stochastic approximation: Theory and applications
- scientific article; zbMATH DE number 6381764 (Why is no real title available?)
- Approximation by quantization of the filter process and applications to optimal stopping problems under partial observation
- Asymptotically optimal quantization schemes for Gaussian processes on Hilbert spaces
- Convergence of conjugate gradient methods with constant stepsizes
- Multiscale Q-learning with linear function approximation
- scientific article; zbMATH DE number 458932 (Why is no real title available?)
- Stochastic adaptation of importance sampler
- Estimating the position of a moving object based on test disturbance of camera position
- A direct search method for unconstrained quantile-based simulation optimization
- On integer stochastic approximation
- scientific article; zbMATH DE number 4043678 (Why is no real title available?)
- scientific article; zbMATH DE number 4104130 (Why is no real title available?)
- Stochastic approximation with long range dependent and heavy tailed noise
- scientific article; zbMATH DE number 45868 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 48067 (Why is no real title available?)
- On Stochastic Approximation and Credibility
- scientific article; zbMATH DE number 718744 (Why is no real title available?)
- scientific article; zbMATH DE number 721880 (Why is no real title available?)
- Strong diffusion approximations for recursive stochastic algorithms
- Retrospective optimization of mixed-integer stochastic systems using dynamic simplex linear interpolation
- scientific article; zbMATH DE number 1944272 (Why is no real title available?)
- scientific article; zbMATH DE number 1946759 (Why is no real title available?)
- Stochastic recursive algorithms for optimization. Simultaneous perturbation methods
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- Optimal quadratic quantization for numerics: the Gaussian case
- Urn models and differential algebraic equations
- Control of singularly perturbed Markov chains: A numerical study
- Risk-constrained reinforcement learning with percentile risk criteria
This page was built for publication: Stochastic approximation algorithms and applications
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4346705)
