Convergence of stochastic approximation via martingale and converse Lyapunov methods
From MaRDI portal
Publication:6097904
Abstract: In this paper, we study the almost sure boundedness and the convergence of the stochastic approximation (SA) algorithm. At present, most available convergence proofs are based on the ODE method, and the almost sure boundedness of the iterations is an assumption and not a conclusion. In Borkar-Meyn (2000), it is shown that if the ODE has only one globally attractive equilibrium, then under additional assumptions, the iterations are bounded almost surely, and the SA algorithm converges to the desired solution. Our objective in the present paper is to provide an alternate proof of the above, based on martingale methods, which are simpler and less technical than those based on the ODE method. As a prelude, we prove a new sufficient condition for the global asymptotic stability of an ODE. Next we prove a "converse" Lyapunov theorem on the existence of a suitable Lyapunov function with a globally bounded Hessian, for a globally exponentially stable system. Both theorems are of independent interest to researchers in stability theory. Then, using these results, we provide sufficient conditions for the almost sure boundedness and the convergence of the SA algorithm. We show through examples that our theory covers some situations that are not covered by currently known results, specifically Borkar-Meyn (2000).
Recommendations
- scientific article; zbMATH DE number 1918629
- scientific article; zbMATH DE number 695867
- On the convergence of linear stochastic approximation procedures
- Stability and instability of limit points for stochastic approximation algorithms
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
Cites work
- scientific article; zbMATH DE number 5348356 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 3449561 (Why is no real title available?)
- scientific article; zbMATH DE number 1405930 (Why is no real title available?)
- scientific article; zbMATH DE number 3302557 (Why is no real title available?)
- A Stochastic Approximation Method
- A stability criterion for two timescale stochastic approximation schemes
- An analysis of temporal-difference learning with function approximation
- Analysis of recursive stochastic algorithms
- Applications of a Kushner and Clark lemma to general classes of stochastic algorithms
- Bounds for Solutions of Ordinary Differential Equations
- New converse Lyapunov theorems and related results on exponential stability
- Nonlinear Systems Analysis
- Nonlinear systems.
- Stochastic approximation
- Stochastic approximation methods for constrained and unconstrained systems
- Strong convergence of a stochastic approximation algorithm
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
- Two models for analyzing the dynamics of adaptation algorithms
Cited in
(7)- Stability and instability of limit points for stochastic approximation algorithms
- On the convergence, lock-in probability, and sample complexity of stochastic approximation
- scientific article; zbMATH DE number 1918629 (Why is no real title available?)
- Convergence of Markovian stochastic approximation with discontinuous dynamics
- Convergence of stochastic approximation via martingale and converse Lyapunov methods
- Convergence rates for stochastic approximation: biased noise with unbounded variance, and applications
- A concentration bound for stochastic approximation via Alekseev's formula
This page was built for publication: Convergence of stochastic approximation via martingale and converse Lyapunov methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097904)
