{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T22:07:35Z","timestamp":1785276455670,"version":"3.55.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T00:00:00Z","timestamp":1669161600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T00:00:00Z","timestamp":1669161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071108"],"award-info":[{"award-number":["12071108"]}],"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":["11671116"],"award-info":[{"award-number":["11671116"]}],"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":["12021001"],"award-info":[{"award-number":["12021001"]}],"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":["11991021"],"award-info":[{"award-number":["11991021"]}],"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":["11991020"],"award-info":[{"award-number":["11991020"]}],"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":["11971372"],"award-info":[{"award-number":["11971372"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Strategic Priority Research Program of CAS","award":["XDA27000000"],"award-info":[{"award-number":["XDA27000000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11701137"],"award-info":[{"award-number":["11701137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Optim Appl"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s10589-022-00432-5","type":"journal-article","created":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T10:18:39Z","timestamp":1669198719000},"page":"531-572","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Distributed stochastic gradient tracking methods with momentum acceleration for non-convex optimization"],"prefix":"10.1007","volume":"84","author":[{"given":"Juan","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9829-3395","authenticated-orcid":false,"given":"Xin-Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yakui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhua","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,23]]},"reference":[{"issue":"9","key":"432_CR1","doi-asserted-by":"publisher","first-page":"4286","DOI":"10.1109\/TW.2013.072313.120739","volume":"12","author":"G Tychogiorgos","year":"2013","unstructured":"Tychogiorgos, G., Gkelias, A., Leung, K.K.: A non-convex distributed optimization framework and its application to wireless ad-hoc networks. IEEE Trans. Wireless Commun. 12(9), 4286\u20134296 (2013)","journal-title":"IEEE Trans. Wireless Commun."},{"key":"432_CR2","unstructured":"Olshevsky,\u00a0A.: Efficient information aggregation strategies for distributed control and signal processing. Phd thesis, Massachusetts Inst. Tech. (2010)"},{"issue":"1","key":"432_CR3","first-page":"11","volume":"3","author":"S Boyd","year":"2011","unstructured":"Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1), 11\u201322 (2011)","journal-title":"Found. Trends Mach. Learn."},{"issue":"3","key":"432_CR4","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2020.2970170","volume":"37","author":"T Chang","year":"2020","unstructured":"Chang, T., Hong, M., Wai, H., Zhang, X., Lu, S.: Distributed learning in the nonconvex world: From batch data to streaming and beyond. IEEE Signal Process. Mag. 37(3), 26\u201338 (2020)","journal-title":"IEEE Signal Process. Mag."},{"issue":"2","key":"432_CR5","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"key":"432_CR6","unstructured":"Assran, M., Loizou,\u00a0N., Ballas,\u00a0N., Rabbat,\u00a0M.: Stochastic gradient push for distributed deep learning. In: Proc. 36th Int. Conf. Mach. Learn. pp. 344\u2013353 (2019)"},{"key":"432_CR7","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"1","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. statist. 1, 400\u2013407 (1951)","journal-title":"Ann. Math. statist."},{"key":"432_CR8","doi-asserted-by":"crossref","unstructured":"Yan,\u00a0Y., Yang,T., Li,\u00a0Z., Lin,\u00a0Q., Yang,\u00a0Y.: A unified analysis of stochastic momentum methods for deep learning. In: Proc. Int. Joint Conf. Artif. Intell. pp. 2955\u20132961 (2018)","DOI":"10.24963\/ijcai.2018\/410"},{"key":"432_CR9","unstructured":"Sutskever,\u00a0T., Martens,\u00a0J., Dahl,\u00a0G., Hinton,\u00a0G.: On the importance of initialization and momentum in deep learning. In: Int. Conf. Mach. Learn. pp. 1139\u20131147 (2013)"},{"key":"432_CR10","unstructured":"Liu,\u00a0Y., Gao,\u00a0Y., Yin,\u00a0W.: An improved analysis of stochastic gradient descent with momentum. In: Proc. Adv. Neural Inf. Process. Syst. pp. 6\u201312 (2020)"},{"key":"432_CR11","unstructured":"Gitman,\u00a0I., Lang,\u00a0H., Zhang,\u00a0P., Xiao,\u00a0L.: Understanding the role of momentum in stochastic gradient methods. In: Proc. Adv. Neural Inf. Process. Syst. pp. 9633\u20139643 (2019)"},{"key":"432_CR12","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10107-015-0871-8","volume":"156","author":"S Ghadimi","year":"2016","unstructured":"Ghadimi, S., Lan, G.: Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Math. Program. 156, 59\u201399 (2016)","journal-title":"Math. Program."},{"issue":"1","key":"432_CR13","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/TAC.2008.2009515","volume":"54","author":"A Nedi\u0107","year":"2009","unstructured":"Nedi\u0107, A., Ozdaglar, A.: Distributed subgradient methods for multi-agent optimization. IEEE Trans. Autom. Control 54(1), 48\u201361 (2009)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"3","key":"432_CR14","doi-asserted-by":"publisher","first-page":"1835","DOI":"10.1137\/130943170","volume":"26","author":"K Yuan","year":"2016","unstructured":"Yuan, K., Ling, Q., Yin, W.: On the convergence of decentralized gradient descent. SIAM J. Optim. 26(3), 1835\u20131854 (2016)","journal-title":"SIAM J. Optim."},{"issue":"21","key":"432_CR15","doi-asserted-by":"publisher","first-page":"5417","DOI":"10.1109\/TSP.2013.2278149","volume":"61","author":"E Ghadimi","year":"2013","unstructured":"Ghadimi, E., Shames, I., Johansson, M.: Multi-step gradient methods for networked optimization. IEEE Trans. Signal Process. 61(21), 5417\u20135429 (2013)","journal-title":"IEEE Trans. Signal Process."},{"issue":"5","key":"432_CR16","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1109\/TAC.2014.2298712","volume":"59","author":"D Jakoveti\u0107","year":"2014","unstructured":"Jakoveti\u0107, D., Xavier, J., Moura, J.M.F.: Fast distributed gradient methods. IEEE Trans. Autom. Control 59(5), 1131\u20131146 (2014)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"4","key":"432_CR17","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1137\/16M1084316","volume":"27","author":"A Nedi\u0107","year":"2017","unstructured":"Nedi\u0107, A., Olshevsky, A., Shi, W.: Achieving geometric convergence for distributed optimization over time-varying graphs. SIAM J. Optim. 27(4), 2597\u20132633 (2017)","journal-title":"SIAM J. Optim."},{"key":"432_CR18","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0J., Zhu,\u00a0S., Soh,\u00a0Y.C., Xie,\u00a0L.: Augmented distributed gradient methods for multi-agent optimization under uncoordinated constant stepsizes. In: Proc. 54th IEEE Conf. Decis. Control (CDC) pp. 2055\u20132060 (2015)","DOI":"10.1109\/CDC.2015.7402509"},{"issue":"4","key":"432_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3256-x","volume":"65","author":"J Gao","year":"2022","unstructured":"Gao, J., Liu, X.W., Dai, Y.H., Huang, Y.K., Yang, P.: Achieving geometric convergence for distributed optimization with Barzilai-Borwein step sizes. Sci. China Inf. Sci. 65(4), 149203 (2022)","journal-title":"Sci. China Inf. Sci."},{"key":"432_CR20","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/s10589-019-00131-8","volume":"74","author":"D Jakoveti\u0107","year":"2019","unstructured":"Jakoveti\u0107, D., Kreji\u0107, N., Krklec Jerinki\u0107, N.: Exact spectral-like gradient method for distributed optimization. Comput. Optim. Appl. 74, 703\u2013728 (2019)","journal-title":"Comput. Optim. Appl."},{"issue":"6","key":"432_CR21","doi-asserted-by":"publisher","first-page":"2627","DOI":"10.1109\/TAC.2019.2942513","volume":"65","author":"R Xin","year":"2020","unstructured":"Xin, R., Khan, U.A.: Distributed heavy-ball: A generalization and acceleration of first-order methods with gradient tracking. IEEE Trans. Autom. Control 65(6), 2627\u20132633 (2020)","journal-title":"IEEE Trans. Autom. Control"},{"key":"432_CR22","doi-asserted-by":"publisher","first-page":"2566","DOI":"10.1109\/TAC.2019.2937496","volume":"65","author":"G Qu","year":"2020","unstructured":"Qu, G., Li, N.: Accelerated distributed Nesterov gradient descent. IEEE Trans. Autom. Control 65, 2566\u20132581 (2020)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"12","key":"432_CR23","doi-asserted-by":"publisher","first-page":"5723","DOI":"10.1109\/TNNLS.2020.3027381","volume":"32","author":"H Li","year":"2021","unstructured":"Li, H., Cheng, H., Wang, Z., Wu, G.C.: Distributed Nesterov gradient and heavy-ball double accelerated asynchronous optimization. IEEE Trans. Neural Netw. Learn. Syst. 32(12), 5723\u20135737 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"432_CR24","doi-asserted-by":"crossref","unstructured":"Shen,\u00a0Y., Yang,\u00a0S.: A heavy-ball distributed optimization algorithm over digraphs with row-stochastic matrices. In: 2020 39th Chinese Control Conf. pp. 4977\u20134982 (2020)","DOI":"10.23919\/CCC50068.2020.9188385"},{"key":"432_CR25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3160684","author":"J Gao","year":"2022","unstructured":"Gao, J., Liu, X.W., Dai, Y.H., Huang, Y.K., Yang, P.: A family of distributed momentum methods over directed graphs with linear convergence. IEEE Trans. Autom. Control (2022). https:\/\/doi.org\/10.1109\/TAC.2022.3160684","journal-title":"IEEE Trans. Autom. Control"},{"issue":"10","key":"432_CR26","doi-asserted-by":"publisher","first-page":"6258","DOI":"10.1109\/TSMC.2019.2960770","volume":"51","author":"Q L\u00fc","year":"2021","unstructured":"L\u00fc, Q., Liao, X., Li, H., Huang, T.: A Nesterov-like gradient tracking algorithm for distributed optimization over directed networks. IEEE Trans. Syst. Man Cybern. Syst. 51(10), 6258\u20136270 (2021)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"4","key":"432_CR27","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1109\/TAC.2014.2363299","volume":"60","author":"D Jakoveti\u0107","year":"2015","unstructured":"Jakoveti\u0107, D., Moura, J.M., Xavier, J.: Linear convergence rate of a class of distributed augmented lagrangian algorithms. IEEE Trans. Autom. Control 60(4), 922\u2013936 (2015)","journal-title":"IEEE Trans. Autom. Control"},{"key":"432_CR28","doi-asserted-by":"crossref","unstructured":"Mansoori,\u00a0F., Wei,\u00a0E.: A general framework of exact primal-dual first-order algorithms for distributed optimization. In: 2019 IEEE Conf. Decis. Control pp. 6386\u20136391 (2019)","DOI":"10.1109\/CDC40024.2019.9029902"},{"issue":"11","key":"432_CR29","doi-asserted-by":"publisher","first-page":"2834","DOI":"10.1109\/TSP.2018.2818081","volume":"66","author":"J Zeng","year":"2018","unstructured":"Zeng, J., Yin, W.: On nonconvex decentralized gradient descent. IEEE Trans. Signal Process. 66(11), 2834\u20132848 (2018)","journal-title":"IEEE Trans. Signal Process."},{"issue":"2","key":"432_CR30","first-page":"120","volume":"2","author":"PD Lorenzo","year":"2016","unstructured":"Lorenzo, P.D., Scutari, G.: Next: In-network nonconvex optimization. IEEE Trans. Signal Inf. Process. Netw. Process. 2(2), 120\u2013136 (2016)","journal-title":"IEEE Trans. Signal Inf. Process. Netw. Process."},{"issue":"4","key":"432_CR31","first-page":"3029","volume":"30","author":"A Daneshmand","year":"2020","unstructured":"Daneshmand, A., Scutari, G., Kungurtsev, V.: Second-order guarantees of distributed gradient algorithms. Comput. Math. Model. 30(4), 3029\u20133068 (2020)","journal-title":"Comput. Math. Model."},{"issue":"8","key":"432_CR32","doi-asserted-by":"publisher","first-page":"4289","DOI":"10.1109\/TSP.2012.2198470","volume":"60","author":"J Chen","year":"2012","unstructured":"Chen, J., Sayed, A.H.: Diffusion adaptation strategies for distributed optimization and learning over networks. IEEE Trans. Signal Process. 60(8), 4289\u20134305 (2012)","journal-title":"IEEE Trans. Signal Process."},{"key":"432_CR33","doi-asserted-by":"publisher","first-page":"4352","DOI":"10.1109\/TSP.2020.3008605","volume":"68","author":"K Yuan","year":"2020","unstructured":"Yuan, K., Alghunaim, S.A., Ying, B., Sayed, A.H.: On the influence of bias-correction on distributed stochastic optimization. IEEE Trans. Signal Process. 68, 4352\u20134367 (2020)","journal-title":"IEEE Trans. Signal Process."},{"issue":"1","key":"432_CR34","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s10107-020-01487-0","volume":"187","author":"S Pu","year":"2021","unstructured":"Pu, S., Nedi\u0107, A.: Distributed stochastic gradient tracking methods. Math. Program. 187(1), 409\u2013457 (2021)","journal-title":"Math. Program."},{"key":"432_CR35","unstructured":"Johnson,\u00a0R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Proc. Adv. Neural Inf. Process Syst. pp. 315\u2013323 (2013)"},{"key":"432_CR36","unstructured":"Nguyen,\u00a0L.M., Liu, J., Scheinberg, K., Tak\u00e1,\u00a0M.: SARAH: A novel method for machine learning problems using stochastic recursive gradient. In: Proc. Int. Conf. Mach. Learn. pp. 2613\u20132621 (2017)"},{"issue":"1","key":"432_CR37","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/TETCI.2020.3017242","volume":"6","author":"H Li","year":"2022","unstructured":"Li, H., Zheng, L., Wang, Z., Yan, Y., Feng, L., Guo, J.: S-DIGing: A stochastic gradient tracking algorithm for distributed optimization. IEEE Trans. Emerg. Top. Comput. Intell. 6(1), 53\u201365 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"432_CR38","first-page":"1","volume":"21","author":"B Li","year":"2020","unstructured":"Li, B., Cen, S., Chen, Y., Chi, Y.: Communication-efficient distributed optimization in networks with gradient tracking and variance reduction. J. Mach. Learn. Res. 21, 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"432_CR39","doi-asserted-by":"publisher","first-page":"6255","DOI":"10.1109\/TSP.2020.3031071","volume":"68","author":"R Xin","year":"2020","unstructured":"Xin, R., Khan, U.A., Kar, S.: Variance-reduced decentralized stochastic optimization with accelerated convergence. IEEE Trans. Signal Process. 68, 6255\u20136271 (2020)","journal-title":"IEEE Trans. Signal Process."},{"issue":"11","key":"432_CR40","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1631\/FITEE.2000615","volume":"22","author":"B Sun","year":"2021","unstructured":"Sun, B., Hu, J., Xia, D., Li, H.: A distributed stochastic optimization algorithm with gradient-tracking and distributed heavy-ball acceleration. Front. Inform. Technol. Electron. Eng. 22(11), 1463\u20131476 (2021)","journal-title":"Front. Inform. Technol. Electron. Eng."},{"issue":"2","key":"432_CR41","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1002\/asjc.2483","volume":"24","author":"J Hu","year":"2022","unstructured":"Hu, J., Xia, D., Cheng, H., Feng, L., Ji, L., Guo, J., Li, H.: A decentralized Nesterov gradient method for stochastic optimization over unbalanced directed networks. Asian J. Control 24(2), 576\u2013593 (2022)","journal-title":"Asian J. Control"},{"key":"432_CR42","doi-asserted-by":"crossref","unstructured":"Erofeeva,\u00a0V., Granichin,\u00a0O., Sergeenko,\u00a0A.: Distributed stochastic optimization with heavy-ball momentum term for parameter estimation. In: Proc. 2021 5th Scientific School Dynamics of Complex Networks and their Applications (DCNA) pp. 69\u201372 (2021)","DOI":"10.1109\/DCNA53427.2021.9586829"},{"key":"432_CR43","unstructured":"Lian,\u00a0X., Zhang,\u00a0C., Zhang,\u00a0H., Hsieh,\u00a0C., Zhang,\u00a0W., Liu,\u00a0J.: Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent. In: Proc. Adv. Neural Inf. Process. Syst. pp. 5330\u20135340 (2017)"},{"key":"432_CR44","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1109\/TSP.2021.3050858","volume":"69","author":"S Vlaski","year":"2021","unstructured":"Vlaski, S., Sayed, A.H.: Distributed learning in non-convex environments-part I: Agreement at a linear rate. IEEE Trans. Signal Process. 69, 1242\u20131256 (2021)","journal-title":"IEEE Trans. Signal Process."},{"key":"432_CR45","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1109\/TSP.2021.3050840","volume":"69","author":"S Vlaski","year":"2021","unstructured":"Vlaski, S., Sayed, A.H.: Distributed learning in non-convex environments-part II: Polynomial escape from saddle-points. IEEE Trans. Signal Process. 69, 1257\u20131270 (2021)","journal-title":"IEEE Trans. Signal Process."},{"key":"432_CR46","unstructured":"Tang,\u00a0H., Lian,\u00a0X., Yan,\u00a0M., Zhang,\u00a0C., Liu,\u00a0J.: D$$^2$$: Decentralized training over decentralized data. In: Proc. 35th Int. Conf. Mach. Learn. pp. 4848\u20134856 (2018)"},{"key":"432_CR47","doi-asserted-by":"crossref","unstructured":"Lu,\u00a0S., Zhang,\u00a0X., Sun,\u00a0H., Hong,\u00a0M.: Gnsd: a gradient-tracking based nonconvex stochastic algorithm for decentralized optimization. In: Proc. 2019 IEEE Data Sci. Workshop pp. 315\u2013321 (2019)","DOI":"10.1109\/DSW.2019.8755807"},{"key":"432_CR48","doi-asserted-by":"publisher","first-page":"1842","DOI":"10.1109\/TSP.2021.3062553","volume":"69","author":"R Xin","year":"2021","unstructured":"Xin, R., Khan, U.A., Kar, S.: An improved convergence analysis for decentralized online stochastic non-convex optimization. IEEE Trans. Signal Process. 69, 1842\u20131858 (2021)","journal-title":"IEEE Trans. Signal Process."},{"key":"432_CR49","unstructured":"Zhang,\u00a0J., You,\u00a0K.: Decentralized stochastic gradient tracking for non-convex empirical risk minimization. ArXiv preprint arXiv:1909.02712 (2019)"},{"issue":"1","key":"432_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/20M1361158","volume":"32","author":"R Xin","year":"2022","unstructured":"Xin, R., Khan, U.A., Kar, S.: Fast decentralized non-convex finite-sum optimization with recursive variance reduction. SIAM J. Optim. 32(1), 1\u201328 (2022)","journal-title":"SIAM J. Optim."},{"key":"432_CR51","unstructured":"Yu,\u00a0H., Jin,\u00a0R., Yang,\u00a0S.: On the linear speedup analysis of communication efficient momentum sgd for distributed non-convex optimization. In: Proc. Int. Conf. Mach. Learn. pp. 7184\u20137193 (2019)"},{"issue":"4","key":"432_CR52","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1137\/120880811","volume":"23","author":"S Ghadimi","year":"2012","unstructured":"Ghadimi, S., Lan, G.: Stochastic first- and zeroth-order methods for nonconvex stochastic programming. SIAM J. Optim. 23(4), 2341\u20132368 (2012)","journal-title":"SIAM J. Optim."},{"key":"432_CR53","volume-title":"Introduction to optimization","author":"BT Polyak","year":"1987","unstructured":"Polyak, B.T.: Introduction to optimization. Optimization Software Inc, New York (1987)"},{"key":"432_CR54","doi-asserted-by":"crossref","unstructured":"Ghadimi,\u00a0E., Feyzmahdavian,\u00a0H.R., Johansson,\u00a0M.: Global convergence of the heavy-ball method for convex optimization. In: Proc. 2015 Eur. Control Conf. pp. 310\u2013315 (2015)","DOI":"10.1109\/ECC.2015.7330562"},{"key":"432_CR55","volume-title":"Introductory lectures on convex optimization: A basic course","author":"Y Nesterov","year":"2013","unstructured":"Nesterov, Y.: Introductory lectures on convex optimization: A basic course. Springer Science & Business Media, UK (2013)"},{"issue":"2","key":"432_CR56","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.automatica.2009.10.021","volume":"46","author":"M Zhu","year":"2010","unstructured":"Zhu, M., Martinez, S.: Discrete-time dynamic average consensus. Automatica 46(2), 322\u2013329 (2010)","journal-title":"Automatica"},{"key":"432_CR57","unstructured":"Sun,\u00a0H., Lu,\u00a0S., Hong,\u00a0H.: Improving the sample and communication complexity for decentralized nonconvex optimization: Joint gradient estimation and tracking. In: Proc. Int. Conf. Mach. Learn. pp. 9217\u20139228 (2020)"},{"key":"432_CR58","doi-asserted-by":"publisher","first-page":"290","DOI":"10.5486\/PMD.1959.6.3-4.12","volume":"6","author":"P Erdos","year":"1959","unstructured":"Erdos, P., Renyi, A.: On random graphs i. Publ. Math. Debrecen 6, 290\u2013297 (1959)","journal-title":"Publ. Math. Debrecen"}],"container-title":["Computational Optimization and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-022-00432-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10589-022-00432-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-022-00432-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T06:00:32Z","timestamp":1676613632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10589-022-00432-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,23]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["432"],"URL":"https:\/\/doi.org\/10.1007\/s10589-022-00432-5","relation":{},"ISSN":["0926-6003","1573-2894"],"issn-type":[{"value":"0926-6003","type":"print"},{"value":"1573-2894","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,23]]},"assertion":[{"value":"29 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 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 that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}