Analysis of recursive stochastic algorithms
From MaRDI portal
Publication:4137045
DOI10.1109/TAC.1977.1101561zbMath0362.93031OpenAlexW2125812768MaRDI QIDQ4137045
Publication date: 1977
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/tac.1977.1101561
Adaptive control/observation systems (93C40) Estimation and detection in stochastic control theory (93E10)
Related Items
Generalized neural networks for spectral analysis: dynamics and Liapunov functions ⋮ Alternative learning vector quantization ⋮ An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method ⋮ Distributed system identification for linear stochastic systems with binary sensors ⋮ Self-tuning control application to a nuclear power plant ⋮ Stochastic approximation to understand simple simulation models ⋮ Convergence and logarithm laws of self-tuning regulators ⋮ Convergence analysis of a simple minor component analysis algorithm ⋮ Convergence of the least-squares method with a polynomial regularizer for the infinite-dimensional autoregression equation ⋮ Stochastic Perturbation Methods for Spike-Timing-Dependent Plasticity ⋮ Rates of convergence of semi-stochastic approximation procedures for solving stochastic optimization problems ⋮ Approximate consensus in the dynamic stochastic network with incomplete information and measurement delays ⋮ Stochastic Methods for Composite and Weakly Convex Optimization Problems ⋮ Unnamed Item ⋮ Convergence rate of least-squares identification and adaptive control for stochastic systems† ⋮ Continuous-time constrained least-squares algorithms for recursive parameter estimation of stochastic linear systems by a stabilized output-error method ⋮ Distributed communications in collision channels with errors ⋮ Recursive identification algorithm for dynamic systems with output backlash and its convergence ⋮ The method of averaged models for discrete-time adaptive systems ⋮ Non-linear system identification using neural networks ⋮ Stochastic quasi-Newton with line-search regularisation ⋮ Book review of: P.R. Kumar and P. Varaiya, Stochastic systems: estimation, identification, and adaptive control ⋮ A time-varying model of rational learning ⋮ Unnamed Item ⋮ Convergence analysis of smoothed stochastic gradient-type algorithm ⋮ Artificial neural networks: an econometric perspective∗ ⋮ Deep limits of residual neural networks ⋮ A back propagation algorithm to estimate the parameters of nonlinear dynamic rational models. ⋮ A competitive layer model for cellular neural networks ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ Fast adaptive algorithms and networks for class-separability features. ⋮ ESTIMATING STRUCTURAL PARAMETERS IN REGRESSION MODELS WITH ADAPTIVE LEARNING ⋮ Convergence analysis of deterministic discrete time system of a unified self-stabilizing algorithm for PCA and MCA ⋮ Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement ⋮ Network flows that solve least squares for linear equations ⋮ When can a deterministic model of a population system reveal what will happen on average? ⋮ Learning strict Nash equilibria through reinforcement ⋮ Reinforcement learning for long-run average cost. ⋮ Continuous-time stochastic approximation: Convergence and asymptotic efficiency ⋮ A review of fuzzy logic and neural network based intelligent control design for discrete-time systems ⋮ A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm ⋮ Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization ⋮ Rates of convergence of adaptive step-size of stochastic approximation algorithms ⋮ Adaptive learning of rational expectations using neural networks ⋮ Unnamed Item ⋮ Stability and chaos of LMSER PCA learning algorithm ⋮ Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate ⋮ Global convergence of a PCA learning algorithm with a constant learning rate ⋮ Prospect-theoretic Q-learning ⋮ Robust hebbian learning and noisy principal component analysis ⋮ Theoretical analysis of the batch variant of the self-organizing feature map algorithm for 1-d networks mapping a continuous 1-d input space ⋮ Simple ‘ in structure ’ estimation algorithm for space–dependent parameters in noisy distributed parameter systems ⋮ Adaptive consumption behavior ⋮ Popularity signals in trial-offer markets with social influence and position bias ⋮ Global convergence of an adaptive minor component extraction algorithm ⋮ Recursive online EM estimation of mixture autoregressions ⋮ Recursive parameter estimation of transfer function models ⋮ Algorithms and networks for accelerated convergence of adaptive LDA ⋮ A new algorithm for recursive estimation of parameters in controlled ARMA processes ⋮ Optimization based on information containing uncertainties ⋮ Stochastic approximation on Riemannian manifolds ⋮ Nonlinear randomized urn models: a stochastic approximation viewpoint ⋮ Learning when to say no ⋮ A self-stabilizing MSA algorithm in high-dimension data stream ⋮ Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces ⋮ Exponential convergence of distributed primal-dual convex optimization algorithm without strong convexity ⋮ Some Examples of Stochastic Approximation in Communications ⋮ Stochastic approximation: from statistical origin to big-data, multidisciplinary applications ⋮ Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning ⋮ Convergence of an adaptive filter algorithm ⋮ Empirical Dynamic Programming ⋮ Time-varying parameters and nonconvergence to rational expectations under least squares learning ⋮ Event-driven stochastic approximation ⋮ Incremental without replacement sampling in nonconvex optimization ⋮ Optimization via simulation: A review ⋮ On the convergence of an associative learning algorithm in the presence of noise ⋮ Joint state and parameter robust estimation of stochastic nonlinear systems ⋮ On the absence of positive realness conditions in self-tuning regulators based on explicit criterion minimization ⋮ Adaptive dynamics in games played by heterogeneous populations ⋮ Revisiting the ODE method for recursive algorithms: fast convergence using quasi stochastic approximation ⋮ Self-tuning controller design for systems with arbitrary time delays Part 2. Algorithms and simulation examples ⋮ An ODE method to prove the geometric convergence of adaptive stochastic algorithms ⋮ Convergence and asymptotic behaviour of parallel algorithms ⋮ An analysis of convergence for a learning version of the subspace method ⋮ Variable forgetting factors in parameter estimation ⋮ Variance constrained self-tuning control ⋮ Self-tuning prediction and control ⋮ Adaptive control of a Wiener type system: application of a pH Neutralization reactor ⋮ Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents ⋮ Recursive estimation of a drifted autoregressive parameter. ⋮ Adaptive optimization and \(D\)-optimum experimental design. ⋮ Introduction to learning and bounded rationality. (Preface to the special issue.) ⋮ Learning aspiration in repeated games ⋮ Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning ⋮ The RPEs of RBCs and other DSGEs ⋮ Design and convergence analysis of stochastic model reference adaptive controllers ⋮ Gradient procedures for stochastic approximation with dependent noise and their asymptotic behaviour ⋮ Identification of ‘ moving average’ plants under unobservable disturbances ⋮ Adaptive control of a class of linear stochastic systems with continuous and discrete unknown parameters ⋮ Active identification of dynamic systems in face of ‘ coloured ’ disturbances ⋮ Convergence analysis of ladder algorithms for AR and ARMA models ⋮ Induction of categories: The problem of multiple equilibria ⋮ Linear filtering with adaptive adjustment of the disturbance covariation matrices in the plant and measurement noise ⋮ Optimal load sharing in soft real-time systems using likelihood ratios ⋮ Sequential online subsampling for thinning experimental designs ⋮ Robust adaptive modified Newton algorithm for generalized eigendecomposition and its application ⋮ Convergence of least squares learning to a non-stationary equilibrium ⋮ Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds ⋮ Convergence analysis for recursive Hammerstein identification ⋮ Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design ⋮ A combined algorithm for identification and approximation ⋮ Strong consistency of recursive identification by no use of persistent excitation condition ⋮ Adaptive filters with constraints and correlated non-stationary signals ⋮ On the optimal control of stochastic linear systems with contaminated partial observations ⋮ Limiting optimal adaptive filtering with unknown disturbance covariance ⋮ Recursive estimators with Markovian jumps ⋮ Self-tuning leader-follower games ⋮ On a proof of Robbins-Monro algorithm ⋮ RLS parameter convergence with overparameterized models ⋮ Convergence of least squares learning mechanisms in self-referential linear stochastic models ⋮ Online learning via congregational gradient descent ⋮ Abstract stochastic approximations and applications ⋮ Parametric and nonparametric curve fitting ⋮ Adaptive multiple minor directions extraction in parallel using a PCA neural network ⋮ Least mean squares learning in self-referential linear stochastic models ⋮ Extremum seeking under stochastic noise and applications to mobile sensors ⋮ Convergence analysis of the OJAn MCA learning algorithm by the deterministic discrete time method ⋮ A theoretical analysis of recursive identification methods ⋮ A new adaptive recursive RLS-based fast-array IIR filter for active noise and vibration control systems ⋮ The effect of the time-structure of information on the expectational-stability of rational expectations ⋮ E-equilibria and adaptive expectations: Output and inflation in the LBS model ⋮ Stochastic fictitious play with continuous action sets ⋮ State inverse and decorrelated state stochastic approximation ⋮ Recursive output error identification algorithms theory and evaluation ⋮ Strong convergence of least squares learning to rational expectations ⋮ Free energy computations by minimization of Kullback-Leibler divergence: An efficient adaptive biasing potential method for sparse representations ⋮ Comments on 'Non-convergence of the approximate maximum likelihood identification algorithm ⋮ Parameter estimation for continuous-time models - a survey ⋮ Analysis of a general recursive prediction error identification algorithm ⋮ Stochastic algorithms for computing means of probability measures ⋮ A self-tuning regulator for multivariable systems ⋮ A modified extended Kalman filter for linear discrete-time systems with unknown parameters ⋮ Recursive prediction error algorithms without a stability test ⋮ Robustness of multipredictor adaptive regulators: MUSMAR ⋮ Convergence analysis of the least-squares identification algorithm with a variable forgetting factor for time-varying linear systems ⋮ Stochastic approximation with discontinuous dynamics and state dependent noise: w.p. 1 and weak convergence ⋮ Some properties of the output error method ⋮ Weighted least squares based recursive parametric identification for the submodels of a PWARX system ⋮ MINLIP for the identification of monotone Wiener systems ⋮ Self-tuning control of a chip refiner motor load ⋮ Stabilization of stochastic approximation by step size adaptation ⋮ Eigenvalue location of certain matrices arising in convergence analysis problems ⋮ Strong consistency of parameter estimates in direct self-tuning control algorithms based on stochastic approximation ⋮ A simplified neuron model as a principal component analyzer ⋮ Stochastic adaptive control using a modified least squares algorithm ⋮ Contractivity of a Markov operator on the space of normalised positive distributions ⋮ Parameter adaptive control algorithms - a tutorial ⋮ A stochastic Kaczmarz algorithm for network tomography ⋮ Control: a perspective ⋮ Lacunary systems and generalized linear processes ⋮ System identification techniques for adaptive signal processing ⋮ Stochastic approximation with dependent noise ⋮ Asymptotic properties of projections with applications to stochastic regression problems ⋮ Simplified descripton of slow-in-the-average Markov walks ⋮ On learning dynamics underlying the evolution of learning rules ⋮ A note on least-squares learning mechanism ⋮ Recursive identification of time-varying systems via incremental estimation ⋮ Locally optimal adaptive control without persistent excitation ⋮ On the discrete time dynamics of a self-stabilizing MCA learning algorithm ⋮ Adaptive predictive control with mean-square input constraint ⋮ Stochastic approximation, cooperative dynamics and supermodular games ⋮ Approximating nonlinear fading-memory operators using neural network models ⋮ Determinacy and stability under learning of rational expectations equilibria ⋮ Distributed learning and cooperative control for multi-agent systems ⋮ Adaptive algorithms for first principal eigenvector computation ⋮ The modified gain extended Kalman filter and parameter identification in linear systems ⋮ Theory and applications of selftuning regulators ⋮ Recusrsive prediction error identification using the nonlinear Wiener model ⋮ A Kalman-tracking filter approach to nonlinear programming ⋮ Adaptation and tracking in system identification - a survey ⋮ Equilibrium with signal extraction from endogenous variables ⋮ Topological orbital equivalence with asymptotic phase for a two time- scales discrete-time system ⋮ Deterministic approximation of best-response dynamics for the matching pennies game ⋮ Stochastic gradient learning in the cobweb model ⋮ Grouping for optimal growth ⋮ Speculative dynamics with bounded rationality learning ⋮ Stochastic approximation algorithms with constant step size whose average is cooperative ⋮ Convergence of learning algorithms without a projection facility ⋮ Theory and applications of adaptive control - a survey ⋮ Stochastic identification and digital control of a heat exchanger: a simulation test case ⋮ Payoff assessments without probabilities: a simple dynamic model of choice ⋮ Adaptive control based on explicit criterion minimization ⋮ Will the self-tuning approach work for general cost criteria? ⋮ Closed loop parameter identifiability and adaptive control of a linear stochastic system ⋮ Asymptotic normality of the continuous-time stochastic approximation algorithm ⋮ Adaptive RLS algorithms under stochastic excitation. - Strong consistency analysis ⋮ Simulated annealing type algorithms for multivariate optimization ⋮ Enhancement of fixed controllers via adaptive-Q disturbance estimate feedback ⋮ Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissant ⋮ Deterministic convergence of a Clarke-Gawthrop self-tuning controller ⋮ Identification of time‐varying OE models in presence of non‐Gaussian noise: Application to pneumatic servo drives ⋮ Asynchronous stochastic approximation with differential inclusions ⋮ A New Recursive Estimation Method for Single Input Single Output Models ⋮ Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning ⋮ Transfer-RLS method and transfer-FORCE learning for simple and fast training of reservoir computing models ⋮ Convergence of stochastic approximation via martingale and converse Lyapunov methods ⋮ Stochastic approximation with discontinuous dynamics, differential inclusions, and applications ⋮ Online Covariance Matrix Estimation in Stochastic Gradient Descent ⋮ Recursive parameter estimation algorithm of the Dirichlet hidden Markov model ⋮ Unnamed Item ⋮ Unnamed Item ⋮ A model for data transmission and its optimization ⋮ Pathological Subgradient Dynamics ⋮ Convergence of the Kiefer–Wolfowitz algorithm in the presence of discontinuities ⋮ Convergence of gradient algorithms for nonconvex \(C^{1+ \alpha}\) cost functions ⋮ Modeling and control of data transmission ⋮ High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling ⋮ Continuous Newton-like Methods Featuring Inertia and Variable Mass ⋮ Unnamed Item ⋮ Online surrogate problem methodology for stochastic discrete resource allocation problem. ⋮ Stochastic approximation ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ Convergence of least squares learning in self-referential discontinuous stochastic models. ⋮ A sensitivity formula for risk-sensitive cost and the actor-critic algorithm ⋮ Recursive identification under scarce measurements-convergence analysis ⋮ Discussion on: ``A stacked model structure for off-line parameter variation estimation in multi-equilibria nonlinear systems ⋮ An Inertial Newton Algorithm for Deep Learning ⋮ Investment decisions when utility depends on wealth and other attributes ⋮ A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization ⋮ Null space gradient flows for constrained optimization with applications to shape optimization ⋮ Convergence of Recursive Stochastic Algorithms Using Wasserstein Divergence ⋮ A generalized Pólya's urn with graph based interactions
