{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T10:43:52Z","timestamp":1758105832177,"version":"3.44.0"},"reference-count":65,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12271272"],"award-info":[{"award-number":["12271272"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1016\/j.ins.2023.119808","type":"journal-article","created":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T11:37:43Z","timestamp":1698147463000},"page":"119808","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["High-dimensional M-estimation for Byzantine-robust decentralized learning"],"prefix":"10.1016","volume":"653","author":[{"given":"Xudong","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2530-883X","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2023.119808_br0010","first-page":"8632","article-title":"A little is enough: circumventing defenses for distributed learning","volume":"32","author":"Baruch","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2023.119808_br0020","first-page":"473","article-title":"Personalized and private peer-to-peer machine learning","volume":"84","author":"Bellet","year":"2018","journal-title":"Int. Conf. Artif. Intell. Statist."},{"key":"10.1016\/j.ins.2023.119808_br0030","first-page":"119","article-title":"Machine learning with adversaries: byzantine tolerant gradient descent","volume":"30","author":"Blanchard","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3\u20134","key":"10.1016\/j.ins.2023.119808_br0040","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1561\/2200000050","article-title":"Convex optimization: algorithms and complexity","volume":"8","author":"Bubeck","year":"2015","journal-title":"Found. Trends\u00ae Mach. Learn."},{"issue":"9","key":"10.1016\/j.ins.2023.119808_br0050","doi-asserted-by":"crossref","first-page":"8639","DOI":"10.1109\/TVT.2021.3102121","article-title":"Bdfl: a byzantine-fault-tolerance decentralized federated learning method for autonomous vehicle","volume":"70","author":"Chen","year":"2021","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"10.1016\/j.ins.2023.119808_br0060","first-page":"7432","article-title":"Distributed high-dimensional regression under a quantile loss function","volume":"21","author":"Chen","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.ins.2023.119808_br0070","series-title":"Annual International Conference on the Theory and Applications of Cryptographic Techniques","first-page":"375","article-title":"Distributed differential privacy via shuffling","author":"Cheu","year":"2019"},{"key":"10.1016\/j.ins.2023.119808_br0080","first-page":"1388","article-title":"Gossip dual averaging for decentralized optimization of pairwise functions","volume":"48","author":"Colin","year":"2016","journal-title":"Int. Conf. Mach. Learn."},{"issue":"2","key":"10.1016\/j.ins.2023.119808_br0090","first-page":"120","article-title":"Next: in-network nonconvex optimization","volume":"2","author":"Di Lorenzo","year":"2016","journal-title":"IEEE Trans. Signal Inf. Process. Netw."},{"issue":"9","key":"10.1016\/j.ins.2023.119808_br0100","doi-asserted-by":"crossref","first-page":"2694","DOI":"10.1109\/JSAC.2022.3191347","article-title":"Basil: a fast and byzantine-resilient approach for decentralized training","volume":"40","author":"Elkordy","year":"2022","journal-title":"IEEE J. Sel. Areas Commun."},{"issue":"456","key":"10.1016\/j.ins.2023.119808_br0110","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1198\/016214501753382273","article-title":"Variable selection via nonconcave penalized likelihood and its oracle properties","volume":"96","author":"Fan","year":"2001","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.ins.2023.119808_br0120","first-page":"610","article-title":"Bridge: byzantine-resilient decentralized gradient descent","volume":"8","author":"Fang","year":"2022","journal-title":"IEEE Trans. Signal Inf. Process. Netw."},{"key":"10.1016\/j.ins.2023.119808_br0130","series-title":"29th USENIX Security Symposium (USENIX Security 20)","first-page":"1605","article-title":"Local model poisoning attacks to byzantine-robust federated learning","author":"Fang","year":"2020"},{"issue":"3","key":"10.1016\/j.ins.2023.119808_br0140","doi-asserted-by":"crossref","first-page":"942","DOI":"10.1109\/JSAIT.2021.3105076","article-title":"Communication-efficient and byzantine-robust distributed learning with error feedback","volume":"2","author":"Ghosh","year":"2021","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"issue":"6","key":"10.1016\/j.ins.2023.119808_br0150","doi-asserted-by":"crossref","first-page":"4096","DOI":"10.1109\/TCSVT.2021.3116976","article-title":"Byzantine-resilient decentralized stochastic gradient descent","volume":"32","author":"Guo","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"year":"2015","series-title":"Statistical Learning with Sparsity: The Lasso and Generalizations","author":"Hastie","key":"10.1016\/j.ins.2023.119808_br0160"},{"author":"He","key":"10.1016\/j.ins.2023.119808_br0170"},{"key":"10.1016\/j.ins.2023.119808_br0180","first-page":"1","article-title":"Credibility assessment based byzantine-resilient decentralized learning","author":"Hou","year":"2022","journal-title":"IEEE Trans. Dependable Secure Comput."},{"author":"Hu","key":"10.1016\/j.ins.2023.119808_br0190"},{"key":"10.1016\/j.ins.2023.119808_br0200","first-page":"5311","article-title":"Learning from history for byzantine robust optimization","volume":"139","author":"Karimireddy","year":"2021","journal-title":"Int. Conf. Mach. Learn."},{"key":"10.1016\/j.ins.2023.119808_br0210","first-page":"3252","article-title":"Error feedback fixes signsgd and other gradient compression schemes","volume":"97","author":"Karimireddy","year":"2019","journal-title":"Int. Conf. Mach. Learn."},{"author":"Konan","key":"10.1016\/j.ins.2023.119808_br0220"},{"author":"Kuwaranancharoen","key":"10.1016\/j.ins.2023.119808_br0230"},{"issue":"3","key":"10.1016\/j.ins.2023.119808_br0240","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1145\/357172.357176","article-title":"The byzantine generals problem","volume":"4","author":"Lamport","year":"1982","journal-title":"ACM Trans. Program. Lang. Syst."},{"issue":"2","key":"10.1016\/j.ins.2023.119808_br0250","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1214\/19-AOS1828","article-title":"Robust machine learning by median-of-means: theory and practice","volume":"48","author":"Lecu\u00e9","year":"2020","journal-title":"Ann. Stat."},{"key":"10.1016\/j.ins.2023.119808_br0260","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.ins.2023.119808_br0270","first-page":"5336","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume":"30","author":"Lian","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2023.119808_br0280","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume":"54","author":"McMahan","year":"2017","journal-title":"Artif. Intell. Stat."},{"issue":"3","key":"10.1016\/j.ins.2023.119808_br0290","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/MSP.2020.2975210","article-title":"Distributed gradient methods for convex machine learning problems in networks: distributed optimization","volume":"37","author":"Nedic","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"issue":"5","key":"10.1016\/j.ins.2023.119808_br0300","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1109\/JPROC.2018.2817461","article-title":"Network topology and communication-computation tradeoffs in decentralized optimization","volume":"106","author":"Nedi\u0107","year":"2018","journal-title":"Proc. IEEE"},{"issue":"1","key":"10.1016\/j.ins.2023.119808_br0310","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TAC.2008.2009515","article-title":"Distributed subgradient methods for multi-agent optimization","volume":"54","author":"Nedic","year":"2009","journal-title":"IEEE Trans. Autom. Control"},{"issue":"3","key":"10.1016\/j.ins.2023.119808_br0320","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1561\/2400000003","article-title":"Proximal algorithms","volume":"1","author":"Parikh","year":"2014","journal-title":"Found. Trends\u00ae Optim."},{"key":"10.1016\/j.ins.2023.119808_br0330","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2021.108020","article-title":"Byzantine-robust decentralized stochastic optimization over static and time-varying networks","volume":"183","author":"Peng","year":"2021","journal-title":"Signal Process."},{"author":"Peng","key":"10.1016\/j.ins.2023.119808_br0340"},{"key":"10.1016\/j.ins.2023.119808_br0350","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1109\/TSP.2022.3153135","article-title":"Robust aggregation for federated learning","volume":"70","author":"Pillutla","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.ins.2023.119808_br0360","first-page":"1216","article-title":"Optimal statistical rates for decentralised non-parametric regression with linear speed-up","volume":"32","author":"Richards","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2023.119808_br0370","first-page":"8105","article-title":"Decentralised learning with random features and distributed gradient descent","volume":"119","author":"Richards","year":"2020","journal-title":"Int. Conf. Mach. Learn."},{"issue":"5","key":"10.1016\/j.ins.2023.119808_br0380","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1137\/0314056","article-title":"Monotone operators and the proximal point algorithm","volume":"14","author":"Rockafellar","year":"1976","journal-title":"SIAM J. Control Optim."},{"issue":"5","key":"10.1016\/j.ins.2023.119808_br0390","first-page":"4641","article-title":"Federated learning with cooperating devices: a consensus approach for massive iot networks","volume":"7","author":"Savazzi","year":"2020","journal-title":"IEEE Int. Things J."},{"issue":"4\u20135","key":"10.1016\/j.ins.2023.119808_br0400","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1561\/2200000051","article-title":"Adaptation, learning, and optimization over networks","volume":"7","author":"Sayed","year":"2014","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"10.1016\/j.ins.2023.119808_br0410","first-page":"4424","article-title":"Federated multi-task learning","volume":"30","author":"Smith","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.ins.2023.119808_br0420","doi-asserted-by":"crossref","first-page":"2227","DOI":"10.1109\/TAC.2020.3008139","article-title":"Byzantine-resilient multiagent optimization","volume":"66","author":"Su","year":"2020","journal-title":"IEEE Trans. Autom. Control"},{"issue":"529","key":"10.1016\/j.ins.2023.119808_br0430","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1080\/01621459.2018.1543124","article-title":"Adaptive huber regression","volume":"115","author":"Sun","year":"2020","journal-title":"J. Am. Stat. Assoc."},{"author":"Sun","key":"10.1016\/j.ins.2023.119808_br0440"},{"issue":"2","key":"10.1016\/j.ins.2023.119808_br0450","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1016\/j.jfranklin.2022.11.004","article-title":"Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion","volume":"360","author":"Tao","year":"2023","journal-title":"J. Franklin Inst."},{"issue":"1","key":"10.1016\/j.ins.2023.119808_br0460","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc., Ser. B, Methodol."},{"issue":"10","key":"10.1016\/j.ins.2023.119808_br0470","doi-asserted-by":"crossref","first-page":"3773","DOI":"10.1007\/s10994-021-06001-x","article-title":"Byzantine-robust distributed sparse learning for m-estimation","volume":"112","author":"Tu","year":"2023","journal-title":"Mach. Learn."},{"key":"10.1016\/j.ins.2023.119808_br0480","doi-asserted-by":"crossref","DOI":"10.1016\/j.isatra.2023.07.043","article-title":"Q-learning based fault estimation and fault tolerant iterative learning control for mimo systems","author":"Wang","year":"2023","journal-title":"ISA Trans."},{"key":"10.1016\/j.ins.2023.119808_br0490","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"3","key":"10.1016\/j.ins.2023.119808_br0500","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1080\/07350015.2022.2074426","article-title":"Network gradient descent algorithm for decentralized federated learning","volume":"41","author":"Wu","year":"2023","journal-title":"J. Bus. Econ. Stat."},{"key":"10.1016\/j.ins.2023.119808_br0510","doi-asserted-by":"crossref","first-page":"3179","DOI":"10.1109\/TSP.2023.3300629","article-title":"Byzantine-resilient decentralized stochastic optimization with robust aggregation rules","volume":"71","author":"Wu","year":"2023","journal-title":"IEEE Trans. Signal Process."},{"author":"Xie","key":"10.1016\/j.ins.2023.119808_br0520"},{"key":"10.1016\/j.ins.2023.119808_br0530","first-page":"261","article-title":"Fall of empires: breaking byzantine-tolerant sgd by inner product manipulation","volume":"115","author":"Xie","year":"2020","journal-title":"Uncertainty Artif. Intell."},{"key":"10.1016\/j.ins.2023.119808_br0540","first-page":"5253","article-title":"Byzantine-resilient decentralized collaborative learning","author":"Xu","year":"2022","journal-title":"Int. Conf. Acoust. Speech Signal Proc."},{"issue":"2","key":"10.1016\/j.ins.2023.119808_br0550","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1109\/TAC.2017.2730481","article-title":"Convergence of asynchronous distributed gradient methods over stochastic networks","volume":"63","author":"Xu","year":"2017","journal-title":"IEEE Trans. Autom. Control"},{"issue":"4","key":"10.1016\/j.ins.2023.119808_br0560","first-page":"611","article-title":"Byrdie: byzantine-resilient distributed coordinate descent for decentralized learning","volume":"5","author":"Yang","year":"2019","journal-title":"IEEE Trans. Signal Inf. Process. Netw."},{"author":"Ye","key":"10.1016\/j.ins.2023.119808_br0570"},{"key":"10.1016\/j.ins.2023.119808_br0580","first-page":"5650","article-title":"Byzantine-robust distributed learning: towards optimal statistical rates","volume":"80","author":"Yin","year":"2018","journal-title":"Int. Conf. Mach. Learn."},{"issue":"3","key":"10.1016\/j.ins.2023.119808_br0590","doi-asserted-by":"crossref","first-page":"1835","DOI":"10.1137\/130943170","article-title":"On the convergence of decentralized gradient descent","volume":"26","author":"Yuan","year":"2016","journal-title":"SIAM J. Optim."},{"issue":"2","key":"10.1016\/j.ins.2023.119808_br0600","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1214\/09-AOS729","article-title":"Nearly unbiased variable selection under minimax concave penalty","volume":"38","author":"Zhang","year":"2010","journal-title":"Ann. Stat."},{"key":"10.1016\/j.ins.2023.119808_br0610","first-page":"2541","article-title":"On model selection consistency of lasso","volume":"7","author":"Zhao","year":"2006","journal-title":"J. Mach. Learn. Res."},{"issue":"18","key":"10.1016\/j.ins.2023.119808_br0620","doi-asserted-by":"crossref","first-page":"10139","DOI":"10.1002\/rnc.6354","article-title":"Robust point-to-point iterative learning control for constrained systems: a minimum energy approach","volume":"32","author":"Zhou","year":"2022","journal-title":"Int. J. Robust Nonlinear Control"},{"key":"10.1016\/j.ins.2023.119808_br0630","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109312","article-title":"Communication-efficient and byzantine-robust distributed learning with statistical guarantee","volume":"137","author":"Zhou","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2023.119808_br0640","first-page":"3151","article-title":"Byzantine-robust federated learning with optimal statistical rates","volume":"206","author":"Zhu","year":"2023","journal-title":"Int. Conf. Artif. Intell. Statist."},{"issue":"6","key":"10.1016\/j.ins.2023.119808_br0650","doi-asserted-by":"crossref","first-page":"3461","DOI":"10.1109\/TSMC.2022.3225381","article-title":"An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints","volume":"53","author":"Zhuang","year":"2023","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025523013932?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025523013932?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:15:12Z","timestamp":1758089712000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025523013932"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":65,"alternative-id":["S0020025523013932"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2023.119808","relation":{},"ISSN":["0020-0255"],"issn-type":[{"type":"print","value":"0020-0255"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"High-dimensional M-estimation for Byzantine-robust decentralized learning","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2023.119808","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"119808"}}