Answers are grounded in this paper and cite their sources.
The paper gives convergence theorems for several sequential Monte-Carlo or stochastic approximation algorithms for finding a local minimum of a function f(•) on a set C defined by C = : qⁱ(x) 0, i = 1, 2, ⋯, s\. f(•) is unknown, but "noise perturbed" values can be observed at any desired parameter x ∈ C. The algorithms generate a sequence of random variables ₙ\ such that (for a.a. ω) any convergent subsequence of ₙ(ω)\ converges to a point where a certain necessary condition for constrained optimality holds. The techniques are drawn from both stochastic approximation, and non-linear programming.
No takes yet. Share an insight, caveat, or question.
Harold J. Kushner (1974) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: