A strong approximation theorem for stochastic recursive algorithms

DOI10.1023/A:1022630321574zbMath0949.62071MaRDI QIDQ1289391

Vivek S. Borkar, Sanjoy K. Mitter

Publication date: 28 November 2000

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

zbMATH Keywords

asymptotic behaviorstochastic algorithmsapproximation of stochastic differential equationsconstant stepsize algorithms

Mathematics Subject Classification ID

Related Items (6)

Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration ⋮ A general view on double limits in differential equations ⋮ Swarm gradient dynamics for global optimization: the mean-field limit case ⋮ Improving sampling accuracy of stochastic gradient MCMC methods via non-uniform subsampling of gradients ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ Stability of annealing schemes and related processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Ergodic control of multidimensional diffusions. II: Adaptive control
• Markov chains and stochastic stability
• Mimicking the one-dimensional marginal distributions of processes having an Ito differential
• A remark on the attainable distributions of controlled diffusions
• Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $
• Metropolis-Type Annealing Algorithms for Global Optimization in $\mathbb{R}^d $
• Bounds for the fundamental solution of a parabolic equation

This page was built for publication: A strong approximation theorem for stochastic recursive algorithms