Back to Search
Start Over
Distributed Coupled Multiagent Stochastic Optimization
- Source :
- IEEE Transactions on Automatic Control. 65:175-190
- Publication Year :
- 2020
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2020.
-
Abstract
- This paper develops an effective distributed strategy for the solution of constrained multiagent stochastic optimization problems with coupled parameters across the agents. In this formulation, each agent is influenced by only a subset of the entries of a global parameter vector or model, and is subject to convex constraints that are only known locally. Problems of this type arise in several applications, most notably in disease propagation models, minimum-cost flow problems, distributed control formulations, and distributed power system monitoring. This paper focuses on stochastic settings, where a stochastic risk function is associated with each agent and the objective is to seek the minimizer of the aggregate sum of all risks subject to a set of constraints. Agents are not aware of the statistical distribution of the data and, therefore, can only rely on stochastic approximations in their learning strategies. We derive an effective distributed learning strategy that is able to track drifts in the underlying parameter model. A detailed performance and stability analysis is carried out showing that the resulting coupled diffusion strategy converges at a linear rate to an $O(\mu)$ neighborhood of the true penalized optimizer.
- Subjects :
- 0209 industrial biotechnology
Mathematical optimization
multiagent networks
Computer science
Stability (learning theory)
02 engineering and technology
algorithms
Data modeling
Set (abstract data type)
020901 industrial engineering & automation
coupled optimization
model-predictive control
Electrical and Electronic Engineering
convergence
penalty method
Stochastic process
learning-behavior
diffusion
stochastic optimization
diffusion strategy
Computer Science Applications
Model predictive control
Distribution (mathematics)
admm
Flow (mathematics)
consensus
Control and Systems Engineering
networks
Stochastic optimization
distributed optimization
Subjects
Details
- ISSN :
- 23343303 and 00189286
- Volume :
- 65
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Automatic Control
- Accession number :
- edsair.doi.dedup.....68cd60af630c30c43c3ff3773c434aca