{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:14:05Z","timestamp":1743081245534,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819707973"},{"type":"electronic","value":"9789819707980"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-0798-0_23","type":"book-chapter","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T08:03:04Z","timestamp":1709193784000},"page":"398-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parallelized ADMM with\u00a0General Objectives for\u00a0Deep Learning"],"prefix":"10.1007","author":[{"given":"Yanqi","family":"Shi","sequence":"first","affiliation":[]},{"given":"Yu","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Zhigang","family":"Kan","sequence":"additional","affiliation":[]},{"given":"Linbo","family":"Qiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,1]]},"reference":[{"issue":"3","key":"23_CR1","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/s10589-016-9828-y","volume":"64","author":"BP Ames","year":"2016","unstructured":"Ames, B.P., Hong, M.: Alternating direction method of multipliers for penalized zero-variance discriminant analysis. Comput. Optim. Appl. 64(3), 725\u2013754 (2016)","journal-title":"Comput. Optim. Appl."},{"key":"23_CR2","unstructured":"Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J., et al.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends\u00ae Mach. Learn. 3(1), 1\u2013122 (2011)"},{"issue":"3","key":"23_CR3","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/1970392.1970395","volume":"58","author":"EJ Cand\u00e8s","year":"2011","unstructured":"Cand\u00e8s, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM (JACM) 58(3), 11 (2011)","journal-title":"J. ACM (JACM)"},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"3118","DOI":"10.1109\/TSP.2016.2537271","volume":"64","author":"TH Chang","year":"2015","unstructured":"Chang, T.H., Hong, M., Liao, W.C., Wang, X.: Asynchronous distributed ADMM for large-scale optimization-part I: algorithm and convergence analysis. IEEE Trans. Sig. Process. 64, 3118\u20133130 (2015)","journal-title":"IEEE Trans. Sig. Process."},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Chartrand, R., Wohlberg, B.: A nonconvex ADMM algorithm for group sparsity with sparse groups. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6009\u20136013. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638818"},{"key":"23_CR6","unstructured":"Chen, C.C., Yang, C.L., Cheng, H.Y.: Efficient and robust parallel DNN training through model parallelism on multi-GPU platform. arXiv abs\/1809.02839 (2018)"},{"key":"23_CR7","unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: NIPS (2012)"},{"key":"23_CR8","unstructured":"Fortin, M., Glowinski, R.: Augmented Lagrangian methods: applications to the numerical solution of boundary-value problems (1983)"},{"issue":"1","key":"23_CR9","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0898-1221(76)90003-1","volume":"2","author":"D Gabay","year":"1976","unstructured":"Gabay, D., Mercier, B.: A dual algorithm for the solution of nonlinear variational problems via finite element approximation. Comput. Math. Appl. 2(1), 17\u201340 (1976)","journal-title":"Comput. Math. Appl."},{"key":"23_CR10","unstructured":"Glowinski, R., Tallec, P.L.: Augmented Lagrangian and operator-splitting methods in nonlinear mechanics (1987)"},{"issue":"1\u20132","key":"23_CR11","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/s10107-012-0530-2","volume":"141","author":"D Goldfarb","year":"2013","unstructured":"Goldfarb, D., Ma, S., Scheinberg, K.: Fast alternating linearization methods for minimizing the sum of two convex functions. Math. Program. 141(1\u20132), 349\u2013382 (2013)","journal-title":"Math. Program."},{"issue":"1","key":"23_CR12","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1137\/130905010","volume":"35","author":"D Goldfarb","year":"2014","unstructured":"Goldfarb, D., Qin, Z.: Robust low-rank tensor recovery: models and algorithms. SIAM J. Matrix Anal. Appl. 35(1), 225\u2013253 (2014)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"4","key":"23_CR13","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1631\/FITEE.1800566","volume":"21","author":"L Guan","year":"2020","unstructured":"Guan, L., et al.: An efficient parallel and distributed solution to nonconvex penalized linear SVMs. Front. Inf. Technol. Electron. Eng. 21(4), 17 (2020)","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1016\/j.neucom.2020.09.029","volume":"435","author":"L Guan","year":"2021","unstructured":"Guan, L., Yang, Z., Li, D., Lu, X.: pdlADMM: an ADMM-based framework for parallel deep learning training with efficiency. Neurocomputing 435, 264\u2013272 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2020.09.029","journal-title":"Neurocomputing"},{"issue":"2","key":"23_CR15","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1137\/110836936","volume":"50","author":"B He","year":"2012","unstructured":"He, B., Yuan, X.: On the o(1\/n) convergence rate of the Douglas-Rachford alternating direction method. SIAM J. Numer. Anal. 50(2), 700\u2013709 (2012)","journal-title":"SIAM J. Numer. Anal."},{"key":"23_CR16","unstructured":"Huang, F., Chen, S.: Mini-batch stochastic ADMMs for nonconvex nonsmooth optimization. arXiv preprint arXiv:1802.03284 (2018)"},{"key":"23_CR17","unstructured":"Huang, F., Chen, S., Lu, Z.: Stochastic alternating direction method of multipliers with variance reduction for nonconvex optimization. arXiv preprint arXiv:1610.02758 (2016)"},{"key":"23_CR18","unstructured":"Huo, Z., Gu, B., Yang, Q., Huang, H.: Decoupled parallel backpropagation with convergence guarantee. arXiv abs\/1804.10574 (2018)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, S., Mei Lei, Y., Wang, S., Wang, D.: An asynchronous ADMM algorithm for distributed optimization with dynamic scheduling strategy. 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 1\u20138 (2019)","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00016"},{"key":"23_CR20","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. Comput. Sci. (2014)"},{"issue":"3","key":"23_CR21","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1137\/07070111X","volume":"51","author":"TG Kolda","year":"2009","unstructured":"Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455\u2013500 (2009)","journal-title":"SIAM Rev."},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Lan, Q., Qiao, L.B., Wang, Y.J.: Stochastic extra-gradient based alternating direction methods for graph-guided regularized minimization. Front. Inf. Technol. Electron. Eng. (006), 019 (2018)","DOI":"10.1631\/FITEE.1601771"},{"issue":"11","key":"23_CR23","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"issue":"20","key":"23_CR24","doi-asserted-by":"publisher","first-page":"5450","DOI":"10.1109\/TSP.2015.2454476","volume":"63","author":"AP Liavas","year":"2015","unstructured":"Liavas, A.P., Sidiropoulos, N.D.: Parallel algorithms for constrained tensor factorization via alternating direction method of multipliers. IEEE Trans. Sig. Process. 63(20), 5450\u20135463 (2015)","journal-title":"IEEE Trans. Sig. Process."},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Masuyama, Y., Kusano, T., Yatabe, K., Oikawa, Y.: Modal decomposition of musical instrument sound via alternating direction method of multipliers. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 631\u2013635. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462350"},{"key":"23_CR26","unstructured":"Monteiro, R.D., Svaiter, B.F.: Iteration-complexity of block-decomposition algorithms and the alternating minimization augmented Lagrangian method. Manuscript, School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, pp. 30332\u20130205 (2010)"},{"key":"23_CR27","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"HE Robbins","year":"1951","unstructured":"Robbins, H.E.: A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"issue":"2","key":"23_CR28","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1080\/10556788.2012.700713","volume":"29","author":"Y Shen","year":"2014","unstructured":"Shen, Y., Wen, Z., Zhang, Y.: Augmented Lagrangian alternating direction method for matrix separation based on low-rank factorization. Optim. Methods Softw. 29(2), 239\u2013263 (2014)","journal-title":"Optim. Methods Softw."},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Sun, D.L., Fevotte, C.: Alternating direction method of multipliers for non-negative matrix factorization with the beta-divergence. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6201\u20136205. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854796"},{"issue":"20","key":"23_CR30","doi-asserted-by":"publisher","first-page":"5380","DOI":"10.1109\/TSP.2018.2868269","volume":"66","author":"T Sun","year":"2018","unstructured":"Sun, T., Jiang, H., Cheng, L., Zhu, W.: Iteratively linearized reweighted alternating direction method of multipliers for a class of nonconvex problems. IEEE Trans. Sig. Process. 66(20), 5380\u20135391 (2018)","journal-title":"IEEE Trans. Sig. Process."},{"key":"23_CR31","unstructured":"Suzuki, T.: Dual averaging and proximal gradient descent for online alternating direction multiplier method. In: International Conference on Machine Learning, pp. 392\u2013400 (2013)"},{"key":"23_CR32","unstructured":"Taylor, G., Burmeister, R., Xu, Z., Singh, B., Patel, A., Goldstein, T.: Training neural networks without gradients: A scalable ADMM approach. In: International Conference on Machine Learning, pp. 2722\u20132731 (2016)"},{"key":"23_CR33","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop, coursera: neural networks for machine learning. Technical report, University of Toronto (2012)"},{"key":"23_CR34","doi-asserted-by":"publisher","unstructured":"Wang, J., Chai, Z., Cheng, Y., Zhao, L.: Toward model parallelism for deep neural network based on gradient-free ADMM framework. In: Proceedings - IEEE International Conference on Data Mining, ICDM 2020, November, pp. 591\u2013600 (2020). https:\/\/doi.org\/10.1109\/ICDM50108.2020.00068","DOI":"10.1109\/ICDM50108.2020.00068"},{"key":"23_CR35","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.neucom.2022.02.039","volume":"487","author":"J Wang","year":"2022","unstructured":"Wang, J., Li, H., Zhao, L.: Accelerated gradient-free neural network training by multi-convex alternating optimization. Neurocomputing 487, 130\u2013143 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.02.039","journal-title":"Neurocomputing"},{"key":"23_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/978-3-031-05936-0_3","volume-title":"Advances in Knowledge Discovery and Data Mining - PAKDD 2022","author":"J Wang","year":"2022","unstructured":"Wang, J., Zhao, L.: Convergence and applications of ADMM on the multi-convex problems. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds.) PAKDD 2022. LNCS (LNAI), vol. 13281, pp. 30\u201343. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-05936-0_3"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Wang, J., Yu, F., Chen, X., Zhao, L.: ADMM for efficient deep learning with global convergence. arXiv preprint arXiv:1905.13611 (2019)","DOI":"10.1145\/3292500.3330936"},{"issue":"1","key":"23_CR38","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/s10915-018-0757-z","volume":"78","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Yin, W., Zeng, J.: Global convergence of ADMM in nonconvex nonsmooth optimization. J. Sci. Comput. 78(1), 29\u201363 (2019)","journal-title":"J. Sci. Comput."},{"key":"23_CR39","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)"},{"issue":"2","key":"23_CR40","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s11464-012-0194-5","volume":"7","author":"Y Xu","year":"2012","unstructured":"Xu, Y., Yin, W., Wen, Z., Zhang, Y.: An alternating direction algorithm for matrix completion with nonnegative factors. Front. Math. China 7(2), 365\u2013384 (2012)","journal-title":"Front. Math. China"},{"key":"23_CR41","unstructured":"Xu, Z., De, S., Figueiredo, M., Studer, C., Goldstein, T.: An empirical study of ADMM for nonconvex problems. arXiv preprint arXiv:1612.03349 (2016)"},{"issue":"1","key":"23_CR42","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1137\/090777761","volume":"33","author":"J Yang","year":"2011","unstructured":"Yang, J., Zhang, Y.: Alternating direction algorithms for $$\\backslash $$ell_1-problems in compressive sensing. SIAM J. Sci. Comput. 33(1), 250\u2013278 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"23_CR43","unstructured":"Zheng, S., Kwok, J.T.: Stochastic variance-reduced ADMM. arXiv preprint arXiv:1604.07070 (2016)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0798-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T08:12:49Z","timestamp":1731485569000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0798-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819707973","9789819707980"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0798-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tjutanklab.com\/ica3pp2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Online submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"439","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"145","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}