Stochastic Approximation Algorithms for the Local Optimization of Functions with Non Unique Stationary Points,
Abstract
The aim of this paper is the provision of a framework for a practical stochastic unconstrained optimization theory. The results are based on certain concepts of stochastic approximation but are not restricted to those procedures, and aim at incorporating the great flexibility of currently available deterministic-optimizaiton ideas into the stochastic problem, whenever optimization must be done by Monte Carlo or sampling methods. Hills with non-unique stationary points are treated. A framework has been provided, with which convergence of stochastic versions of conjugate gradient, partan, etc. can be discussed and proved. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1971
- Accession Number
- AD0730035
Entities
People
- Harold J. Kushner
Organizations
- Brown University