{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:31:35Z","timestamp":1753893095316,"version":"3.41.2"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Commun. Netw."],"abstract":"<jats:p>As one of the important statistical methods, quantile regression (QR) extends traditional regression analysis. In QR, various quantiles of the response variable are modeled as linear functions of the predictors, allowing for a more flexible analysis of how the predictors affect different parts of the response variable distribution. QR offers several advantages over standard linear regression due to its focus on estimating conditional quantiles rather than the conditional mean of the response variable. This paper investigates QR over sensor networks, where each node has access to a local dataset and collaboratively estimates a global QR model. QR solves a non-smooth optimization problem characterized by a piecewise linear loss function, commonly known as the check function. We reformulate this non-smooth optimization problem as the task of finding a saddle point of a convex\u2013concave objective and develop a distributed primal\u2013dual hybrid gradient (dPDHG) algorithm for this purpose. Theoretical analyses guarantee the convergence of the proposed algorithm under mild assumptions, while experimental results show that the dPDHG algorithm converges significantly faster than subgradient-based schemes.<\/jats:p>","DOI":"10.3389\/frcmn.2025.1604850","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T05:27:52Z","timestamp":1750138072000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Distributed quantile regression over sensor networks via the primal\u2013dual hybrid gradient algorithm"],"prefix":"10.3389","volume":"6","author":[{"given":"Zheng","family":"Qin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoting","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7345","DOI":"10.1109\/TWC.2023.3250263","article-title":"On integrated sensing and communication waveforms with tunable papr","volume":"22","author":"Bazzi","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"B2","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1109\/ACSSC.2017.8335537","article-title":"A Newton-type forward backward greedy method for multi-snapshot compressed sensing","volume-title":"2017 51st asilomar conference on signals, systems, and computers","author":"Bazzi","year":"2017"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2448","DOI":"10.1109\/TSG.2016.2527820","article-title":"Forecasting uncertainty in electricity smart meter data by boosting additive quantile regression","volume":"7","author":"Ben Taieb","year":"2016","journal-title":"IEEE Trans. Smart Grid"},{"key":"B4","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1890\/1540-9295(2003)001[0412:agitqr]2.0.co;2","article-title":"A gentle introduction to quantile regression for ecologists","volume":"1","author":"Cade","year":"2003","journal-title":"Front. Ecol. Environ."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/tsp.2009.2033729","article-title":"Diffusion LMS strategies for distributed estimation","volume":"58","author":"Cattivelli","year":"2010","journal-title":"IEEE Trans. Signal Process."},{"key":"B6","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/s10851-024-01174-1","article-title":"Stochastic primal\u2013dual hybrid gradient algorithm with adaptive step sizes","volume":"66","author":"Chambolle","year":"2024","journal-title":"J. Math. Imaging Vis."},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1109\/Allerton.2012.6483273","article-title":"A fast distributed proximal-gradient method","volume-title":"2012 50th annual allerton Conference on communication, control, and computing (allerton)","author":"Chen","year":"2012"},{"article-title":"MM algorithms for statistical estimation in quantile regression","year":"2024","author":"Cheng","key":"B8"},{"key":"B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/VTC2023-Spring57618.2023.10200157","article-title":"Deep learning-based estimation for multitarget radar detection","volume-title":"2023 IEEE 97th vehicular technology conference (VTC2023-Spring)","author":"Delamou","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1137\/09076934x","article-title":"A general framework for a class of first order primal-dual algorithms for convex optimization in imaging science","volume":"3","author":"Esser","year":"2010","journal-title":"SIAM J. Imaging Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"6328","DOI":"10.1109\/jsyst.2022.3142183","article-title":"Distributed fault-tolerant state estimation for a class of nonlinear systems over sensor networks with sensor faults and random link failures","volume":"16","author":"Gao","year":"2022","journal-title":"IEEE Syst. J."},{"key":"B12","first-page":"2089","article-title":"Adaptive primal-dual splitting methods for statistical learning and image processing","volume-title":"Proceedings of the 29th international conference on neural information processing systems - volume 2","author":"Goldstein","year":"2015"},{"key":"B13","doi-asserted-by":"publisher","first-page":"4682","DOI":"10.1109\/TSP.2024.3474168","article-title":"A distributed adaptive algorithm for non-smooth spatial filtering problems in wireless sensor networks","volume":"72","author":"Hovine","year":"2024","journal-title":"IEEE Trans. Signal Process."},{"key":"B14","doi-asserted-by":"publisher","first-page":"21753","DOI":"10.1109\/TITS.2022.3190194","article-title":"Modeling censored mobility demand through censored quantile regression neural networks","volume":"23","author":"H\u00fcttel","year":"2022","journal-title":"IEEE Trans. Intelligent Transp. Syst."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1080\/10618600.2023.2184374","article-title":"Nonparametric and semiparametric quantile regression via a New MM algorithm","volume":"32","author":"Kai","year":"2023","journal-title":"J. Comput. Graph. Stat."},{"key":"B16","article-title":"Consensus-based distributed quantile estimation in sensor networks","author":"Lee","year":"2018","journal-title":"arXiv Prepr. arXiv:1805.00154"},{"key":"B17","doi-asserted-by":"publisher","first-page":"38","DOI":"10.4018\/ijsst.2020070103","article-title":"ngermanDistributed quantiles estimation of sensor network measurements","volume":"7","author":"Lee","year":"2020","journal-title":"Int. J. Smart Secur. Technol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"4480","DOI":"10.1109\/tsp.2012.2198468","article-title":"Diffusion sparse least-mean squares over networks","volume":"60","author":"Liu","year":"2012","journal-title":"IEEE Trans. Signal Process."},{"key":"B19","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/OJSP.2023.3344395","article-title":"Smoothing admm for sparse-penalized quantile regression with non-convex penalties","volume":"5","author":"Mirzaeifard","year":"2024","journal-title":"IEEE Open J. Signal Process."},{"key":"B20","doi-asserted-by":"publisher","first-page":"69896","DOI":"10.1109\/ACCESS.2022.3187837","article-title":"Dnn-based indoor localization under limited dataset using gans and semi-supervised learning","volume":"10","author":"Njima","year":"2022","journal-title":"IEEE Access"},{"key":"B21","first-page":"1","article-title":"Quantile regression comprehensive in machine learning: a review","volume-title":"2023 IEEE international students\u2019 conference on electrical, electronics and computer science (SCEECS)","author":"Patidar","year":"2023"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1109\/tsp.2009.2016226","article-title":"Distributed LMS for consensus-based in-network adaptive processing","volume":"57","author":"Schizas","year":"2009","journal-title":"IEEE Trans. Signal Process."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1002\/dac.3769","article-title":"Fault diagnosis and its prediction in wireless sensor networks using regressional learning to achieve fault tolerance","volume":"31","author":"Swain","year":"2018","journal-title":"Int. J. Commun. Syst."},{"key":"B24","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1109\/jstsp.2011.2125943","article-title":"Mobile adaptive networks","volume":"5","author":"Tu","year":"2011","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"B25","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1177\/1471082x18759142","article-title":"Quantile regression: a short story on how and why","volume":"18","author":"Waldmann","year":"2018","journal-title":"Stat. Model."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2767","DOI":"10.1109\/TPWRS.2016.2625101","article-title":"Direct quantile regression for nonparametric probabilistic forecasting of wind power generation","volume":"32","author":"Wan","year":"2017","journal-title":"IEEE Trans. Power Syst."},{"key":"B27","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1109\/TSIPN.2017.2699923","article-title":"Distributed quantile regression over sensor networks","volume":"4","author":"Wang","year":"2018","journal-title":"IEEE Trans. Signal Inf. Process. over Netw."},{"key":"B28","doi-asserted-by":"publisher","first-page":"3945","DOI":"10.1109\/TSP.2023.3325622","article-title":"On linear convergence of ADMM for decentralized quantile regression","volume":"71","author":"Wang","year":"2023","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Frontiers in Communications and Networks"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frcmn.2025.1604850\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T05:27:54Z","timestamp":1750138074000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frcmn.2025.1604850\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":28,"alternative-id":["10.3389\/frcmn.2025.1604850"],"URL":"https:\/\/doi.org\/10.3389\/frcmn.2025.1604850","relation":{},"ISSN":["2673-530X"],"issn-type":[{"type":"electronic","value":"2673-530X"}],"subject":[],"published":{"date-parts":[[2025,6,17]]},"article-number":"1604850"}}