English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Big data, including applications with high security requirements, are oftencollected and stored on multiple heterogeneous devices, such as mobile devices,drones and vehicles. Due to the limitations of communication costs and securityrequirements, it is of paramount importance to extract information in adecentralized manner instead of aggregating data to a fusion center. To trainlarge-scale machine learning models, edge/fog computing is often leveraged asan alternative to centralized learning. We consider the problem of learningmodel parameters in a multi-agent system with data locally processed viadistributed edge nodes. A class of mini-batch stochastic alternating directionmethod of multipliers (ADMM) algorithms is explored to develop the distributedlearning model. To address two main critical challenges in distributednetworks, i.e., communication bottleneck and straggler nodes (nodes with slowresponses), error-control-coding based stochastic incremental ADMM isinvestigated. Given an appropriate mini-batch size, we show that the mini-batchstochastic ADMM based method converges in a rate of $O(\frac{1}{\sqrt{k}})$,where $k$ denotes the number of iterations. Through numerical experiments, itis revealed that the proposed algorithm is communication-efficient, rapidlyresponding and robust in the presence of straggler nodes compared with state ofthe art algorithms.

Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge Computing