Distributed Stochastic Approximation with Local Projections
| Autor: | Suhail M. Shah, Vivek S. Borkar |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0209 industrial biotechnology
Regular polygon 020206 networking & telecommunications Systems and Control (eess.SY) 02 engineering and technology Stochastic approximation Theoretical Computer Science 020901 industrial engineering & automation Differential inclusion Intersection Projection (mathematics) Distributed algorithm Scheme (mathematics) FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Computer Science - Systems and Control Applied mathematics Software Mathematics |
| Zdroj: | SIAM Journal on Optimization. 28:3375-3401 |
| ISSN: | 1095-7189 1052-6234 |
| DOI: | 10.1137/17m1128460 |
| Popis: | We propose a distributed version of a stochastic approximation scheme constrained to remain in the intersection of a finite family of convex sets. The projection to the intersection of these sets is also computed in a distributed manner and a `nonlinear gossip' mechanism is employed to blend the projection iterations with the stochastic approximation using multiple time scales 28 pages, 3 figures, submitted to SiOpt |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|