Abstract
We study four conditions on noise sequences for convergence of stochastic approximation algorithms on a general Hilbert space: Kushner and Clark's condition, Chen's condition, Kulkarni and Horn's condition, and a decomposition condition. We discuss various properties of these conditions. In our main result we show that the four conditions are all equivalent, and are both necessary and sufficient for convergence of stochastic approximation algorithms under appropriate assumptions.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 3849-3854 |
| Number of pages | 6 |
| Journal | Proceedings of the IEEE Conference on Decision and Control |
| Volume | 4 |
| State | Published - 1995 |
| Externally published | Yes |
| Event | Proceedings of the 1995 34th IEEE Conference on Decision and Control. Part 1 (of 4) - New Orleans, LA, USA Duration: Dec 13 1995 → Dec 15 1995 |
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Modeling and Simulation
- Control and Optimization