Stochastic Approximation with Discontinuous Dynamics and State Dependent Noise: w.p.1 Convergence.
Abstract
Stochastic approximations might not be continuous and the noise sequence (xi sub n) might depend on (X sub n). An 'averaging' and an 'ordinary differential equation' method are combined to get w.p.1 convergence for both the above algorithm and for the case where the iterates are projected back onto a bounded set G if they ever leave it. Two examples are developed, the first being an automata problem where the dynamics are not smooth and the noise is state dependent, and the second a Robbins-Monro process with observation averaging (which causes the noise to be state dependent). Each example is typical of a larger class.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 10, 1980
- Accession Number
- ADA089777
Entities
People
- Harold J. Kushner
Organizations
- Brown University