A Dynamical System Approach to Stochastic Approximations
From MaRDI portal
Publication:4876712
DOI10.1137/S0363012993253534zbMath0841.62072MaRDI QIDQ4876712
Publication date: 18 July 1996
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
asymptotic behaviorneural networksalmost sure convergenceaveragingchain-recurrencelimit sets of trajectory solutions
Stochastic approximation (62L20) Averaging method for ordinary differential equations (34C29) Asymptotic properties of solutions to ordinary differential equations (34D05) Dynamical systems and ergodic theory (37-XX)
Related Items (49)
Generalized urn models of evolutionary processes. ⋮ Vertex reinforced random walks with exponential interaction on complete graphs ⋮ Broadcast control of multi-agent systems ⋮ Market clearing and price formation ⋮ EQUILIBRIUM, EVOLUTIONARY STABILITY AND GRADIENT DYNAMICS ⋮ Asynchronous stochastic approximation with differential inclusions ⋮ Vertex-reinforced random walks and a conjecture of Pemantle ⋮ Stochastic recursive inclusions with non-additive iterate-dependent Markov noise ⋮ Stochastic approximation with long range dependent and heavy tailed noise ⋮ Two repelling random walks on \(\mathbb{Z}\) ⋮ Stochastic approximation with discontinuous dynamics, differential inclusions, and applications ⋮ Strategic behavior and partial cost sharing. ⋮ A Distributed Boyle--Dykstra--Han Scheme ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ Smale strategies for network prisoner's dilemma games ⋮ Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement ⋮ Asymptotic bias of stochastic gradient search ⋮ Algorithmes stochastiques à bruit dépendant (Dependent noise for stochastic algorithms). ⋮ REPEATED PLAY AND NEWTON'S METHOD ⋮ Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis ⋮ Portfolio management without probabilities or statistics ⋮ ERGODIC PROPERTIES OF WEAK ASYMPTOTIC PSEUDOTRAJECTORIES FOR SET-VALUED DYNAMICAL SYSTEMS ⋮ LEARNING TO FACE STOCHASTIC DEMAND ⋮ Stochastic approximation, cooperative dynamics and supermodular games ⋮ NEWTONIAN MECHANICS AND NASH PLAY ⋮ Stochastic approximation on Riemannian manifolds ⋮ Unnamed Item ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ Competitive equilibrium:walras meets darwin ⋮ Event-driven stochastic approximation ⋮ Asymptotic behavior of Bayesian learners with misspecified models ⋮ Nonlinear Gossip ⋮ Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise ⋮ Mixed equilibria and dynamical systems arising from fictitious play in perturbed games ⋮ Stochastic mean values, rational expectations, and price movements ⋮ Grouping for optimal growth ⋮ Pooling, pricing and trading of risks ⋮ An ODE method to prove the geometric convergence of adaptive stochastic algorithms ⋮ On deregulating food prices ⋮ Strongly vertex-reinforced jump process on a complete graph ⋮ Stochastic modelling of thermal effects on a ferromagnetic nano particle ⋮ Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing ⋮ Time to absorption in discounted reinforcement models. ⋮ Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning ⋮ Convergence of generalized urn models to non-equilibrium attractors ⋮ A generalized Pólya's urn with graph based interactions ⋮ Analyzing Approximate Value Iteration Algorithms ⋮ On Gradient-Based Learning in Continuous Games ⋮ Entropic penalties in finite games
This page was built for publication: A Dynamical System Approach to Stochastic Approximations
