Adaptive Penalty-Based Distributed Stochastic Convex Optimization
From MaRDI portal
Publication:4579353
DOI10.1109/TSP.2014.2331615zbMATH Open1393.90078arXiv1312.4415MaRDI QIDQ4579353FDOQ4579353
Authors: Zaid J. Towfic, Ali H. Sayed 
Publication date: 22 August 2018
Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)
Abstract: In this work, we study the task of distributed optimization over a network of learners in which each learner possesses a convex cost function, a set of affine equality constraints, and a set of convex inequality constraints. We propose a fully-distributed adaptive diffusion algorithm based on penalty methods that allows the network to cooperatively optimize the global cost function, which is defined as the sum of the individual costs over the network, subject to all constraints. We show that when small constant step-sizes are employed, the expected distance between the optimal solution vector and that obtained at each node in the network can be made arbitrarily small. Two distinguishing features of the proposed solution relative to other related approaches is that the developed strategy does not require the use of projections and is able to adapt to and track drifts in the location of the minimizer due to changes in the constraints or in the aggregate cost itself. The proposed strategy is also able to cope with changing network topology, is robust to network disruptions, and does not require global information or rely on central processors.
Full work available at URL: https://arxiv.org/abs/1312.4415
Cited In (8)
- A flocking-based approach for distributed stochastic optimization
- An adaptive penalty-like continuous-time algorithm to constrained distributed convex optimization
- Distributed stochastic gradient tracking methods
- Distributed statistical optimization for non-randomly stored big data with application to penalized learning
- Distributed gradient algorithm for constrained optimization with application to load sharing in power systems
- Tracking-ADMM for distributed constraint-coupled optimization
- Swarming for faster convergence in stochastic optimization
- Distributed constrained optimization via continuous-time mirror design
This page was built for publication: Adaptive Penalty-Based Distributed Stochastic Convex Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4579353)
