Stability and Performance Limits of Adaptive Primal-Dual Networks
From MaRDI portal
Publication:4580602
DOI10.1109/TSP.2015.2415759zbMATH Open1394.94968arXiv1408.3693MaRDI QIDQ4580602FDOQ4580602
Publication date: 22 August 2018
Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)
Abstract: This work studies distributed primal-dual strategies for adaptation and learning over networks from streaming data. Two first-order methods are considered based on the Arrow-Hurwicz (AH) and augmented Lagrangian (AL) techniques. Several revealing results are discovered in relation to the performance and stability of these strategies when employed over adaptive networks. The conclusions establish that the advantages that these methods have for deterministic optimization problems do not necessarily carry over to stochastic optimization problems. It is found that they have narrower stability ranges and worse steady-state mean-square-error performance than primal methods of the consensus and diffusion type. It is also found that the AH technique can become unstable under a partial observation model, while the other techniques are able to recover the unknown under this scenario. A method to enhance the performance of AL strategies is proposed by tying the selection of the step-size to their regularization parameter. It is shown that this method allows the AL algorithm to approach the performance of consensus and diffusion strategies but that it remains less stable than these other strategies.
Full work available at URL: https://arxiv.org/abs/1408.3693
Cited In (3)
- Linear convergence of primal-dual gradient methods and their performance in distributed optimization
- Asymptotic properties of dual averaging algorithm for constrained distributed stochastic optimization
- Asymptotic Properties of Primal-Dual Algorithm for Distributed Stochastic Optimization over Random Networks with Imperfect Communications
This page was built for publication: Stability and Performance Limits of Adaptive Primal-Dual Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4580602)
