Stochastic Approximation and Large Deviations: General Results for W.p.l. Convergence,
Abstract
W.p.l. convergence results are obtained for stochastic recursive approximation algorithms under very general conditions. The gain sequence (a sub n) can go to zero very slowly and state-dependent noise, discontinuous dynamical equations and the projected or constrained algorithm are all treated. The basic technique is the theory of large deviations. Prior results obtained via this theory are extended in many directions. Keywords: Local linearization; Errors for tracking systems.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1987
- Accession Number
- ADA185818
Entities
People
- Harold J. Kushner
- Paul Dupuis
Organizations
- Brown University