Back to Search
Start Over
Distributed Personalized Gradient Tracking with Convex Parametric Models
- Publication Year :
- 2020
- Publisher :
- arXiv, 2020.
-
Abstract
- We present a distributed optimization algorithm for solving online personalized optimization problems over a network of computing and communicating nodes, each of which linked to a specific user. The local objective functions are assumed to have a composite structure and to consist of a known time-varying (engineering) part and an unknown (user-specific) part. Regarding the unknown part, it is assumed to have a known parametric (e.g., quadratic) structure a priori, whose parameters are to be learned along with the evolution of the algorithm. The algorithm is composed of two intertwined components: (i) a dynamic gradient tracking scheme for finding local solution estimates and (ii) a recursive least squares scheme for estimating the unknown parameters via user's noisy feedback on the local solution estimates. The algorithm is shown to exhibit a bounded regret under suitable assumptions. Finally, a numerical example corroborates the theoretical analysis.
- Subjects :
- Cost
Noise measurement
Systems and Control (eess.SY)
Heuristic algorithm
Electrical Engineering and Systems Science - Systems and Control
Computer Science Applications
Cost function
Distributed Optimization
Parametric statistics
Control and Systems Engineering
Optimization and Control (math.OC)
Learning system
FOS: Electrical engineering, electronic engineering, information engineering
FOS: Mathematics
Distributed Learning
Electrical and Electronic Engineering
Online Optimization
Mathematics - Optimization and Control
Gaussian processe
Subjects
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....005aeb7da85c9adbbbcfd424b3310b55
- Full Text :
- https://doi.org/10.48550/arxiv.2008.04363