Some Pathological Traps for Stochastic Approximation
From MaRDI portal
Publication:4210457
DOI10.1137/S036301299630759XzbMath0980.62068OpenAlexW1984209039MaRDI QIDQ4210457
Publication date: 21 September 1998
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/s036301299630759x
Stochastic approximation (62L20) Limit theorems in probability theory (60F99) Neural nets and related approaches to inference from stochastic processes (62M45)
Related Items (10)
Multiscale Q-learning with linear function approximation ⋮ Heterogeneous beliefs and local information in stochastic fictitious play ⋮ Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods ⋮ Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization ⋮ Recursive estimation for ordered eigenvectors of symmetric matrix with observation noise ⋮ Avoidance of traps in stochastic approximation ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ An ODE method to prove the geometric convergence of adaptive stochastic algorithms ⋮ Natural actor-critic algorithms ⋮ Smoothed Functional Algorithms for Stochastic Optimization Using q -Gaussian Distributions
This page was built for publication: Some Pathological Traps for Stochastic Approximation
