{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T17:16:59Z","timestamp":1772817419164,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:00:00Z","timestamp":1656374400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:00:00Z","timestamp":1656374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976243"],"award-info":[{"award-number":["61976243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971458"],"award-info":[{"award-number":["61971458"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2023,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The computational bottleneck in distributed optimization methods, which is based on projected gradient descent, is due to the computation of a full gradient vector and projection step. This is a particular problem for large datasets. To reduce the computational complexity of existing methods, we combine the randomized block-coordinate descent and the Frank\u2013Wolfe techniques, and then propose a distributed randomized block-coordinate projection-free algorithm over networks, where each agent randomly chooses a subset of the coordinates of its gradient vector and the projection step is eschewed in favor of a much simpler linear optimization step. Moreover, the convergence performance of the proposed algorithm is also theoretically analyzed. Specifically, we rigorously prove that the proposed algorithm can converge to optimal point at rate of <jats:inline-formula><jats:alternatives><jats:tex-math>$${\\mathcal {O}}(1\/t)$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mi>O<\/mml:mi>\n                    <mml:mo>(<\/mml:mo>\n                    <mml:mn>1<\/mml:mn>\n                    <mml:mo>\/<\/mml:mo>\n                    <mml:mi>t<\/mml:mi>\n                    <mml:mo>)<\/mml:mo>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> under convexity and <jats:inline-formula><jats:alternatives><jats:tex-math>$${\\mathcal {O}}(1\/t^2)$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mi>O<\/mml:mi>\n                    <mml:mo>(<\/mml:mo>\n                    <mml:mn>1<\/mml:mn>\n                    <mml:mo>\/<\/mml:mo>\n                    <mml:msup>\n                      <mml:mi>t<\/mml:mi>\n                      <mml:mn>2<\/mml:mn>\n                    <\/mml:msup>\n                    <mml:mo>)<\/mml:mo>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> under strong convexity, respectively. Here, <jats:italic>t<\/jats:italic> is the number of iterations. Furthermore, the proposed algorithm can converge to a stationary point, where the \u201cFrank-Wolfe\u201d gap is equal to zero, at a rate <jats:inline-formula><jats:alternatives><jats:tex-math>$${\\mathcal {O}}(1\/\\sqrt{t})$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mi>O<\/mml:mi>\n                    <mml:mo>(<\/mml:mo>\n                    <mml:mn>1<\/mml:mn>\n                    <mml:mo>\/<\/mml:mo>\n                    <mml:msqrt>\n                      <mml:mi>t<\/mml:mi>\n                    <\/mml:msqrt>\n                    <mml:mo>)<\/mml:mo>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> under non-convexity. To evaluate the computational benefit of the proposed algorithm, we use the proposed algorithm to solve the multiclass classification problems by simulation experiments on two datasets, i.e., aloi and news20. The results shows that the proposed algorithm is faster than the existing distributed optimization algorithms due to its lower computation per iteration. Furthermore, the results also show that well-connected graphs or smaller graphs leads to faster convergence rate, which can confirm the theoretical results.<\/jats:p>","DOI":"10.1007\/s40747-022-00785-8","type":"journal-article","created":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T09:02:53Z","timestamp":1656406973000},"page":"267-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks"],"prefix":"10.1007","volume":"9","author":[{"given":"Junlong","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7552-455X","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mingchuan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Muhua","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qingtao","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,28]]},"reference":[{"issue":"3","key":"785_CR1","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1007\/s10957-006-9080-1","volume":"129","author":"L Xiao","year":"2006","unstructured":"Xiao L, Boyd S (2006) Optimal scaling of a gradient method for distributed resource allocation. J Opt Theory Appl 129(3):469\u2013488","journal-title":"J Opt Theory Appl"},{"issue":"1","key":"785_CR2","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/TCNS.2014.2309751","volume":"1","author":"A Beck","year":"2014","unstructured":"Beck A, Nedi\u0107 A, Ozdaglar A, Teboulle M (2014) An $$O\\left(1\/k\\right)$$ gradient method for network resource allocation problems. IEEE Trans Control Netw Syst 1(1):64\u201373","journal-title":"IEEE Trans Control Netw Syst"},{"issue":"9","key":"785_CR3","doi-asserted-by":"crossref","first-page":"2162","DOI":"10.1109\/TAC.2013.2253218","volume":"58","author":"E Wei","year":"2013","unstructured":"Wei E, Ozdaglar A, Jadbabaie A (2013) A distributed newton method for network utility maximization-I: Algorithm. IEEE Trans Autom Control 58(9):2162\u20132175","journal-title":"IEEE Trans Autom Control"},{"key":"785_CR4","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139042918","volume-title":"Scaling up machine learning: parallel and distributed approaches","author":"JLR Bekkerman","year":"2011","unstructured":"Bekkerman JLR, Bilenko M (2011) Scaling up machine learning: parallel and distributed approaches. Cambridge Univ. Press, Cambridge, U.K"},{"issue":"11","key":"785_CR5","doi-asserted-by":"crossref","first-page":"5538","DOI":"10.1109\/TAC.2017.2690401","volume":"62","author":"A Nedi\u0107","year":"2017","unstructured":"Nedi\u0107 A, Olshevsky A, Uribe C (2017) Fast convergence rates for distributed non-bayesian learning. IEEE Trans Autom Control 62(11):5538\u20135553","journal-title":"IEEE Trans Autom Control"},{"issue":"3","key":"785_CR6","doi-asserted-by":"crossref","first-page":"1847","DOI":"10.1109\/TSP.2009.2038417","volume":"58","author":"J Bazerque","year":"2010","unstructured":"Bazerque J, Giannakis G (2010) Distributed spectrum sensing for cognitive radio networks by exploiting sparsity. IEEE Trans Signal Process 58(3):1847\u20131862","journal-title":"IEEE Trans Signal Process"},{"key":"785_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-0363-7","volume-title":"Distributed sensor networks: a multiagent perspective","author":"V Lesser","year":"2003","unstructured":"Lesser V, Ortiz C, Tambe M (2003) Distributed sensor networks: a multiagent perspective. Kluwer Academic Publishers, Norwell, MA"},{"key":"785_CR8","first-page":"20","volume":"26\u201327","author":"M Rabbat","year":"2004","unstructured":"Rabbat M, Nowak R (2004) \u201cDistributed optimization in sensor networks,\u2019\u2019in Proc. ACM IPSN, Berkeley, CA, USA, Apr. 26\u201327:20\u201327","journal-title":"ACM IPSN, Berkeley, CA, USA, Apr."},{"issue":"11","key":"785_CR9","doi-asserted-by":"crossref","first-page":"2703","DOI":"10.1109\/TAC.2012.2190161","volume":"57","author":"H Ishii","year":"2012","unstructured":"Ishii H, Tempo R, Bai E (2012) A web aggregation approach for distributed randomized pagerank algorithms. IEEE Trans Autom Control 57(11):2703\u20132717","journal-title":"IEEE Trans Autom Control"},{"issue":"8","key":"785_CR10","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.1109\/TAC.2013.2250071","volume":"58","author":"I Necoara","year":"2013","unstructured":"Necoara I (2013) Random coordinate descent algorithms for multi-agent convex optimization over networks. IEEE Trans Autom Control 58(8):2001\u20132012","journal-title":"IEEE Trans Autom Control"},{"issue":"2","key":"785_CR11","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1109\/TPWRS.2012.2210288","volume":"28","author":"L Gan","year":"2013","unstructured":"Gan L, Topcu U, Low S (2013) Optimal decentralized protocol for electric vehicle charging. IEEE Trans Power Syst 28(2):940\u2013951","journal-title":"IEEE Trans Power Syst"},{"key":"785_CR12","doi-asserted-by":"crossref","unstructured":"S. Ram, V. Veeravalli, and A. Nedi\u0107, \u201cDistributed non-autonomous power control through distributed convex optimization,\u201din Proc. IEEE INFOCOM, 2009, pp. 3001-3005","DOI":"10.1109\/INFCOM.2009.5062275"},{"key":"785_CR13","unstructured":"J. N. Tsitsiklis, \u201cProblems in decentralized decision making and computation,\u201dPh. D. dissertation, Dept. Elect. Eng. Comp. Sci., Massachusetts Institute of Technology, Cambridge, 1984"},{"issue":"9","key":"785_CR14","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1109\/TAC.1986.1104412","volume":"31","author":"JN Tsitsiklis","year":"1986","unstructured":"Tsitsiklis JN, Bertsekas DP, Athans M (1986) Distributed asynchronous deterministic and stochastic gradient optimization algorithms. IEEE Trans Autom Control 31(9):803\u2013812","journal-title":"IEEE Trans Autom Control"},{"key":"785_CR15","volume-title":"Parallel and distributed computation: numerical methods","author":"DP Bertsekas","year":"1997","unstructured":"Bertsekas DP, Tsitsiklis JN (1997) Parallel and distributed computation: numerical methods. Athena Scientific, Belmont, MA"},{"issue":"1","key":"785_CR16","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TAC.2008.2009515","volume":"54","author":"A Nedi\u0107","year":"2009","unstructured":"Nedi\u0107 A, Ozdaglar A (2009) Distributed subgradient methods for multi-agent optimization. IEEE Trans Autom Control 54(1):48\u201361","journal-title":"IEEE Trans Autom Control"},{"issue":"3","key":"785_CR17","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1109\/TAC.2011.2161027","volume":"57","author":"JC Duchi","year":"2012","unstructured":"Duchi JC, Agarwal A, Wainwright MJ (2012) Dual average for distributed optimization: Convergence analysis and network scaling. IEEE Trans Autom Control 57(3):592\u2013606","journal-title":"IEEE Trans Autom Control"},{"issue":"4","key":"785_CR18","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1109\/TAC.2010.2041686","volume":"55","author":"A Nedi\u0107","year":"2010","unstructured":"Nedi\u0107 A, Ozdaglar A, Parrilo A (2010) Constraint consensus and optimization in multi-agent networks. IEEE Trans Autom Control 55(4):922\u2013938","journal-title":"IEEE Trans Autom Control"},{"issue":"1","key":"785_CR19","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1109\/TCYB.2018.2869249","volume":"50","author":"X He","year":"2020","unstructured":"He X, Yu J, Huang T, Li C, Li C (2020) Average quasi-consensus algorithm for distributed constrained optimization: impulsive communication framework. IEEE Trans Cybern 50(1):351\u2013360","journal-title":"IEEE Trans Cybern"},{"issue":"3","key":"785_CR20","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1109\/TAC.2018.2849616","volume":"64","author":"H Li","year":"2019","unstructured":"Li H, L\u00fc Q, Huang T (2019) Distributed projection subgradient algorithm over time-varying general unbalanced directed graphs. IEEE Trans Autom Control 64(3):1309\u20131316","journal-title":"IEEE Trans Autom Control"},{"key":"785_CR21","doi-asserted-by":"crossref","unstructured":"X. Wen and S. Qin, \u201cA projection-based continuous-time algorithm for distributed optimization over multi-agent systems,\u201dComplex Intell. Syst., 2021","DOI":"10.1007\/s40747-020-00265-x"},{"issue":"1","key":"785_CR22","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1109\/TAC.2021.3056233","volume":"67","author":"G Chen","year":"2022","unstructured":"Chen G, Yang Q, Song Y, Lewis FL (2022) Fixed-time projection algorithm for distributed constrained optimization on time-varying digraphs. IEEE Trans Autom Control 67(1):390\u2013397","journal-title":"IEEE Trans Autom Control"},{"key":"785_CR23","doi-asserted-by":"crossref","first-page":"2611","DOI":"10.1109\/TSP.2021.3070223","volume":"69","author":"SS Alaviani","year":"2021","unstructured":"Alaviani SS, Elia N (2021) Distributed convex optimization with state-dependent (social) interactions and time-varying topologies. IEEE Trans Signal Process 69:2611\u20132624","journal-title":"IEEE Trans Signal Process"},{"issue":"2","key":"785_CR24","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1109\/TAC.2021.3056535","volume":"67","author":"S Chen","year":"2022","unstructured":"Chen S, Garcia A, Shahrampour S (2022) On distributed nonconvex optimization: projected subgradient method for weakly convex problems in networks. IEEE Trans Autom Control 67(2):662\u2013675","journal-title":"IEEE Trans Autom Control"},{"issue":"1\u20132","key":"785_CR25","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1002\/nav.3800030109","volume":"3","author":"M Frank","year":"1956","unstructured":"Frank M, Wolfe P (1956) An algorithm for quadratic programming. Naval Res Logist Quart 3(1\u20132):95\u2013110","journal-title":"Naval Res Logist Quart"},{"key":"785_CR26","unstructured":"M. Jaggi, \u201cRevisiting Frank-Wolfe: Projection-free sparse convex optimization,\u201din Proc. Int. Conf. Mach. Learn., 2013, pp. 427-435"},{"issue":"1\u20132","key":"785_CR27","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s10107-014-0778-9","volume":"152","author":"Z Harchaoui","year":"2015","unstructured":"Harchaoui Z, Juditsky A, Nemirovski A (2015) Conditional gradient algorithms for norm-regularized smooth convex optimization. Math Program 152(1\u20132):75\u2013112","journal-title":"Math Program"},{"issue":"3","key":"785_CR28","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1137\/140985366","volume":"26","author":"D Garber","year":"2016","unstructured":"Garber D, Hazan E (2016) A linearly convergent variant of the conditional gradient algorithm under strong convexity, with applications to online and stochastic optimization. SIAM J Opt 26(3):1493\u20131528","journal-title":"SIAM J Opt"},{"key":"785_CR29","unstructured":"E. Hazan and H. Luo, \u201cVariance-reduced and projection-free stochastic optimization,\u201din Proc. Int. Conf. Mach. Learn., 2016, pp. 1263-1271"},{"key":"785_CR30","doi-asserted-by":"crossref","first-page":"3597","DOI":"10.1109\/TSP.2021.3087910","volume":"69","author":"B Li","year":"2021","unstructured":"Li B, Couti\u00f1o M, Giannakis GB, Leus G (2021) A momentum-guided frank-wolfe algorithm. IEEE Trans Signal Process 69:3597\u20133611","journal-title":"IEEE Trans Signal Process"},{"issue":"11","key":"785_CR31","doi-asserted-by":"crossref","first-page":"5522","DOI":"10.1109\/TAC.2017.2685559","volume":"62","author":"H-T Wai","year":"2017","unstructured":"Wai H-T, Lafond J, Scaglione A, Moulines E (2017) Decentralized Frank-Wolfe algorithm for convex and non-convex problems. IEEE Trans Autom Control 62(11):5522\u20135537","journal-title":"IEEE Trans Autom Control"},{"key":"785_CR32","unstructured":"S. Lacoste-Julien, M. Jaggi, M. Schmidt, and P. Pletscher, \u201cBlock-coordinate Frank-Wolfe optimization for structural SVMs,\u201din Proc. Int. Conf. Mach. Learn., 2013, pp. 53-61"},{"key":"785_CR33","unstructured":"A. Osokin, J.-B. Alayrac, I. Lukasewitz, P. K. Dokania, and S. Lacoste-Julien, Minding the gaps for block Frank-Wolfe optimization of structured SVMs. Proc Int Conf Mach Learn, 2016, pp. 593-602"},{"key":"785_CR34","doi-asserted-by":"crossref","unstructured":"Y. Wang, V. Sadhanala, W. Dai, W. Neiswanger, S. Sra, and E. P. Xing, Parallel and distributed block-coordinate Frank-Wolfe algorithms, In: Proc. Int. Conf. Mach. Learn., 2016, pp. 1548-1557","DOI":"10.1186\/s13637-016-0041-1"},{"issue":"24","key":"785_CR35","doi-asserted-by":"crossref","first-page":"6448","DOI":"10.1109\/TSP.2017.2755597","volume":"65","author":"L Zhang","year":"2017","unstructured":"Zhang L, Wang G, Romero D, Giannakis GB (2017) Randomized block Frank-Wolfe for convergent large-scale learning. IEEE Trans Signal Process 65(24):6448\u20136461","journal-title":"IEEE Trans Signal Process"},{"issue":"1","key":"785_CR36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000016","volume":"3","author":"S Boyd","year":"2011","unstructured":"Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1\u2013122","journal-title":"Found Trends Mach Learn"},{"key":"785_CR37","doi-asserted-by":"crossref","unstructured":"M. Zhang, Y. Zhou, Q. Ge, R. Zheng, and Q. Wu, Decentralized randomized block-coordinate Frank-Wolfe algorithms for submodular maximization over networks, IEEE Trans Syst Man Cybern Syst, early access, 2021","DOI":"10.1109\/TSMC.2021.3112691"},{"issue":"5","key":"785_CR38","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1109\/TAC.2014.2298712","volume":"59","author":"D Jakoveti\u0107","year":"2014","unstructured":"Jakoveti\u0107 D, Xavier J, Moura JMF (2014) Fast distributed gradient methods. IEEE Trans Autom Control 59(5):1131\u20131146","journal-title":"IEEE Trans Autom Control"},{"issue":"2","key":"785_CR39","doi-asserted-by":"crossref","first-page":"944","DOI":"10.1137\/14096668X","volume":"25","author":"W Shi","year":"2015","unstructured":"Shi W, Ling Q, Wu G, Yin W (2015) Extra: an exact first-order algorithm for decentralized consensus optimization. SIAM J Opt 25(2):944\u2013966","journal-title":"SIAM J Opt"},{"issue":"3","key":"785_CR40","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1109\/TCNS.2017.2698261","volume":"5","author":"G Qu","year":"2018","unstructured":"Qu G, Li N (2018) Harnessing smoothness to accelerate distributed optimization. IEEE Trans Control Netw Syst 5(3):1245\u20131260","journal-title":"IEEE Trans Control Netw Syst"},{"issue":"4","key":"785_CR41","doi-asserted-by":"crossref","first-page":"2597","DOI":"10.1137\/16M1084316","volume":"27","author":"A Nedi\u0107","year":"2017","unstructured":"Nedi\u0107 A, Olshevsky A, Shi W (2017) Achieving geometric convergence for distributed optimization over time-varying graphs. J Opt SIAM 27(4):2597\u20132633","journal-title":"J Opt SIAM"},{"issue":"5","key":"785_CR42","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/TAC.2017.2737582","volume":"63","author":"C Xi","year":"2018","unstructured":"Xi C, Xin R, Khan UA (2018) ADD-OPT: Accelerated distributed directed optimization. Autom Control IEEE Trans 63(5):1329\u20131339","journal-title":"Autom Control IEEE Trans"},{"key":"785_CR43","doi-asserted-by":"crossref","first-page":"3500","DOI":"10.1109\/TSP.2021.3083981","volume":"69","author":"F Mansoori","year":"2021","unstructured":"Mansoori F, Wei E (2021) FlexPD: a flexible framework of first-order primal-dual algorithms for distributed optimization. IEEE Trans Signal Process 69:3500\u20133512","journal-title":"IEEE Trans Signal Process"},{"issue":"1","key":"785_CR44","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/TSP.2016.2617829","volume":"65","author":"A Mokhtari","year":"2017","unstructured":"Mokhtari A, Ling Q, Ribeiro A (2017) Network newton distributed optimization methods. IEEE Trans Signal Process 65(1):146\u2013161","journal-title":"IEEE Trans Signal Process"},{"issue":"2","key":"785_CR45","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1137\/15M1038049","volume":"27","author":"D Bajovi\u0107","year":"2017","unstructured":"Bajovi\u0107 D, Jakoveti\u0107 D, Kreji\u0107 N, Jerinki\u0107 NK (2017) Newton-like method with diagonal correction for distributed optimization. SIAM J Opt 27(2):1171\u20131203","journal-title":"SIAM J Opt"},{"issue":"10","key":"785_CR46","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1109\/TSP.2017.2666776","volume":"65","author":"M Eisen","year":"2017","unstructured":"Eisen M, Mokhtari A, Ribeiro A (2017) Decentralized quasi-Newton methods. IEEE Trans Signal Process 65(10):2613\u20132628","journal-title":"IEEE Trans Signal Process"},{"issue":"10","key":"785_CR47","doi-asserted-by":"crossref","first-page":"2718","DOI":"10.1109\/TSP.2013.2254478","volume":"61","author":"JFC Mota","year":"2013","unstructured":"Mota JFC, Xavier JMF, Aguiar PMQ, P\u00fcschel M (2013) D-ADMM: a communication-efficient distributed algorithm for separable optimization. IEEE Trans Signal Process 61(10):2718\u20132723","journal-title":"IEEE Trans Signal Process"},{"issue":"7","key":"785_CR48","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1109\/TSP.2014.2304432","volume":"62","author":"W Shi","year":"2014","unstructured":"Shi W, Ling Q, Yuan K, Wu G, Yin W (2014) On the linear convergence of the admm in decentralized consensus optimization. IEEE Trans Signal Process 62(7):1750\u20131761","journal-title":"IEEE Trans Signal Process"},{"key":"785_CR49","volume-title":"Nonlinear Programming","author":"DP Bertsekas","year":"1999","unstructured":"Bertsekas DP (1999) Nonlinear Programming, 2nd edn. Athena Scientific, Belmout, MA, USA","edition":"2"},{"issue":"2","key":"785_CR50","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1137\/100802001","volume":"22","author":"Y Nesterov","year":"2012","unstructured":"Nesterov Y (2012) Efficiency of coordinate descent methods on huge-scale optimization problems. SIAM J Opt 22(2):341\u2013362","journal-title":"SIAM J Opt"},{"issue":"1\u20132","key":"785_CR51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10107-012-0614-z","volume":"144","author":"P Richt\u00e1rik","year":"2014","unstructured":"Richt\u00e1rik P, Tak\u00e1\u010d M (2014) Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function. Math Program 144(1\u20132):1\u201338","journal-title":"Math Program"},{"issue":"1\u20132","key":"785_CR52","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1007\/s10107-015-0901-6","volume":"156","author":"P Richt\u00e1rik","year":"2016","unstructured":"Richt\u00e1rik P, Tak\u00e1\u010d M (2016) Parallel coordinate descent methods for big data optimization. Math Program 156(1\u20132):433\u2013484","journal-title":"Math Program"},{"key":"785_CR53","doi-asserted-by":"crossref","unstructured":"I. Necoara, \u201cDistributed and parallel random coordinate descent methods for huge convex programming over networks,\u201din Proc. IEEE Conf. Decis. Control, 2015, pp. 425-430","DOI":"10.1109\/CDC.2015.7402237"},{"key":"785_CR54","doi-asserted-by":"crossref","unstructured":"C. Singh, A. Ned\u0107, and R. Srikant, \u201cRandom block-coordinate gradient projection algorithms,\u201din Proc. IEEE Conf. Decis. Control, 2014, pp. 185-190","DOI":"10.1109\/CDC.2014.7039379"},{"issue":"2","key":"785_CR55","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/TSP.2017.2757903","volume":"66","author":"C Wang","year":"2018","unstructured":"Wang C, Zhang Y, Ying B, Sayed AH (2018) Coordinate-descent diffusion learning by network agents. IEEE Trans Signal Process. 66(2):352\u2013367","journal-title":"IEEE Trans Signal Process."},{"key":"785_CR56","doi-asserted-by":"crossref","unstructured":"Notarnicola I, Sun Y, Scutari G, Notarstefano G (2021) Distributed big-data optimization via blockwise gradient tracking. IEEE Trans Autom Control 66(5):2045\u20132060","DOI":"10.1109\/TAC.2020.3008713"},{"issue":"10","key":"785_CR57","doi-asserted-by":"crossref","first-page":"2947","DOI":"10.1109\/TAC.2015.2512043","volume":"61","author":"P Bianchi","year":"2016","unstructured":"Bianchi P, Hachem W, Lutzeler F (2016) A coordinate descent primal-dual algorithm and application to distributed asynchronous optimization. IEEE Trans Autom Control 61(10):2947\u20132957","journal-title":"IEEE Trans Autom Control"},{"issue":"10","key":"785_CR58","doi-asserted-by":"crossref","first-page":"4050","DOI":"10.1109\/TAC.2019.2906924","volume":"64","author":"P Latafat","year":"2019","unstructured":"Latafat P, Freris NM, Patrinos P (2019) A new randomized block-coordinate primal-dual proximal algorithm for distributed optimization. IEEE Trans Autom Control 64(10):4050\u20134065","journal-title":"IEEE Trans Autom Control"},{"key":"785_CR59","unstructured":"J. Lafond, H.-T. Wai, and E. Moulines, \u201cOn the online Frank-Wolfe algorithms for convex and non-convex optimizations,\u201darXiv preprint arXiv: 1510.01171v2, Aug. 2015"},{"key":"785_CR60","doi-asserted-by":"crossref","unstructured":"A. Makhdoumi and A. Ozdaglar, \u201cGraph balancing for distributed subgradient methods over directed graphs,\u201din Proc. IEEE Conf. Decis. Control, 2015, pp. 1364-1371","DOI":"10.1109\/CDC.2015.7402401"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00785-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-022-00785-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00785-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T18:49:52Z","timestamp":1677091792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-022-00785-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,28]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["785"],"URL":"https:\/\/doi.org\/10.1007\/s40747-022-00785-8","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,28]]},"assertion":[{"value":"15 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared no potential conflicts of interest with respect to the research, authorship, and publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}