Asynchronous Adaptation and Learning Over Networks—Part II: Performance Analysis

DOI10.1109/TSP.2014.2385041zbMATH Open1394.94694arXiv1312.5438OpenAlexW2963544917MaRDI QIDQ4579732FDOQ4579732

Authors: Xiaochuan Zhao, Ali H. Sayed 

Publication date: 22 August 2018

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: In Part I cite{Zhao13TSPasync1}, we introduced a fairly general model for asynchronous events over adaptive networks including random topologies, random link failures, random data arrival times, and agents turning on and off randomly. We performed a stability analysis and established the notable fact that the network is still able to converge in the mean-square-error sense to the desired solution. Once stable behavior is guaranteed, it becomes important to evaluate how fast the iterates converge and how close they get to the optimal solution. This is a demanding task due to the various asynchronous events and due to the fact that agents influence each other. In this Part II, we carry out a detailed analysis of the mean-square-error performance of asynchronous strategies for solving distributed optimization and adaptation problems over networks. We derive analytical expressions for the mean-square convergence rate and the steady-state mean-square-deviation. The expressions reveal how the various parameters of the asynchronous behavior influence network performance. In the process, we establish the interesting conclusion that even under the influence of asynchronous events, all agents in the adaptive network can still reach an $O(u^{1+gamm{a_o}^{\prime }})$ near-agreement with some $gamm{a_o}^{\prime }>0$ while approaching the desired solution within $O(u)$ accuracy, where $u$ is proportional to the small step-size parameter for adaptation.

Full work available at URL: https://arxiv.org/abs/1312.5438

Recommendations

• Asynchronous Adaptation and Learning Over Networks—Part III: Comparison Analysis
• Asynchronous Adaptation and Learning Over Networks—Part I: Modeling and Stability Analysis
• On the Learning Behavior of Adaptive Networks—Part II: Performance Analysis
• Adaptation and learning over networks under subspace constraints Part II: Performance Analysis
• Adaptation, learning, and optimization over networks
• Multitask Diffusion Adaptation Over<?Pub _newline ?>Asynchronous Networks
• Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks
• Adaptation and Learning Over Networks Under Subspace Constraints—Part I: Stability Analysis
• Asynchronous stochastic approximation and adaptation in a competitive system
• Convergence of Asynchronous Distributed Gradient Methods Over Stochastic Networks

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Information theory (general) (94A15)

Cited In (3)

• Multitask Diffusion Adaptation Over<?Pub _newline ?>Asynchronous Networks
• Learning PDFA with Asynchronous Transitions
• Adaptation and learning over networks under subspace constraints Part II: Performance Analysis

This page was built for publication: Asynchronous Adaptation and Learning Over Networks—Part II: Performance Analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4579732)