{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:09:27Z","timestamp":1777900167141,"version":"3.51.4"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060952","type":"print"},{"value":"9783032060969","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06096-9_9","type":"book-chapter","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T09:54:15Z","timestamp":1758880455000},"page":"147-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing the\u00a0Optimal Weighted Average: Efficient Distributed Sparse Classification"],"prefix":"10.1007","author":[{"given":"Fred","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan R.","family":"Curtin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Raff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francis","family":"Ferraro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Holt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"9_CR1","unstructured":"Anderson, H.S., Roth, P.: EMBER: an open dataset for training static PE malware machine learning models. arXiv preprint arXiv:1804.04637 (2018)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Andrew, G., Gao, J.: Scalable training of L1-regularized log-linear models. In: 24th International Conference on Machine Learning, pp. 33\u201340 (2007)","DOI":"10.1145\/1273496.1273501"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J., et\u00a0al.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends\u00ae Mach. Learn. 3(1), 1\u2013122 (2011)","DOI":"10.1561\/2200000016"},{"issue":"3","key":"9_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1\u201327 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"1","key":"9_CR5","first-page":"7552","volume":"22","author":"RR Curtin","year":"2021","unstructured":"Curtin, R.R., Edel, M., Prabhu, R.G., Basak, S., Lou, Z., Sanderson, C.: The ensmallen library for flexible numerical optimization. JMLR 22(1), 7552\u20137557 (2021)","journal-title":"JMLR"},{"issue":"82","key":"9_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.21105\/joss.05026","volume":"8","author":"RR Curtin","year":"2023","unstructured":"Curtin, R.R., et al.: MLPACK 4: a fast, header-only C++ machine learning library. J. Open Source Softw. 8(82), 1\u20131 (2023)","journal-title":"J. Open Source Softw."},{"key":"9_CR7","unstructured":"Curtin, R.R., Im, S., Moseley, B., Pruhs, K., Samadian, A.: Unconditional coresets for regularized loss minimization. In: AISTATS 2020, pp. 482\u2013492 (2020)"},{"key":"9_CR8","unstructured":"Dua, D., Graff, C.: UCI ML repository (2017). http:\/\/archive.ics.uci.edu\/ml"},{"key":"9_CR9","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. JMLR 9, 1871\u20131874 (2008)","journal-title":"JMLR"},{"issue":"1","key":"9_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","volume":"33","author":"J Friedman","year":"2010","unstructured":"Friedman, J., Hastie, T., Tibshirani, R.: Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33(1), 1 (2010)","journal-title":"J. Stat. Softw."},{"issue":"5","key":"9_CR11","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1214\/aos\/1015957397","volume":"28","author":"W Fu","year":"2000","unstructured":"Fu, W., Knight, K.: Asymptotics for lasso-type estimators. Ann. Stat. 28(5), 1356\u20131378 (2000)","journal-title":"Ann. Stat."},{"key":"9_CR12","unstructured":"Goldstein, T., Studer, C., Baraniuk, R.: A field guide to forward-backward splitting with a FASTA implementation. arXiv preprint arXiv:1411.3406 (2014)"},{"key":"9_CR13","unstructured":"Gopal, S., Yang, Y.: Distributed training of large-scale logistic models. In: ICML, pp. 289\u2013297 (2013)"},{"issue":"3","key":"9_CR14","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/88.242438","volume":"1","author":"AY Grama","year":"1993","unstructured":"Grama, A.Y., Gupta, A., Kumar, V.: Isoefficiency: measuring the scalability of parallel algorithms and architectures. IEEE Parallel Distrib. Technol. Syst. Appl. 1(3), 12\u201321 (1993)","journal-title":"IEEE Parallel Distrib. Technol. Syst. Appl."},{"issue":"2","key":"9_CR15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"A Halevy","year":"2009","unstructured":"Halevy, A., Norvig, P., Pereira, F.: The unreasonable effectiveness of data. IEEE Intell. Syst. 24(2), 8\u201312 (2009)","journal-title":"IEEE Intell. Syst."},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., Wainwright, M.: Statistical learning with sparsity: the lasso and generalizations (2015)","DOI":"10.1201\/b18401"},{"key":"9_CR17","unstructured":"Huang, J., Ma, S., Zhang, C.H.: The iterated lasso for high-dimensional logistic regression. Univ. Iowa, Dept. Stat. Actuarial Sci. 7, 1\u201320 (2008)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Izbicki, M., Shelton, C.R.: Distributed learning of non-convex linear models with one round of communication. In: ECML PKDD 2019, pp. 197\u2013212 (2020)","DOI":"10.1007\/978-3-030-46147-8_12"},{"key":"9_CR19","unstructured":"Jaggi, M., Smith, V., Tak\u00e1c, M., Terhorst, J., Krishnan, S., Hofmann, T., Jordan, M.I.: Communication-efficient distributed dual coordinate ascent. In: NIPS, vol. 27 (2014)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Jin, R., Li, D., Gao, J., Liu, Z., Chen, L., Zhou, Y.: Towards a better understanding of linear models for recommendation. In: KDD 2021, pp. 776\u2013785 (2021)","DOI":"10.1145\/3447548.3467428"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Jordan, M.I., Lee, J.D., Yang, Y.: Communication-efficient distributed statistical inference. J. Am. Stat. Assoc. 114(526), 668\u2013681 (2018)","DOI":"10.1080\/01621459.2018.1429274"},{"issue":"6245","key":"9_CR22","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1126\/science.aaa8415","volume":"349","author":"MI Jordan","year":"2015","unstructured":"Jordan, M.I., Mitchell, T.M.: Machine learning: trends, perspectives, and prospects. Science 349(6245), 255\u2013260 (2015)","journal-title":"Science"},{"issue":"9","key":"9_CR23","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1038\/s42256-022-00525-0","volume":"4","author":"PH Kassani","year":"2022","unstructured":"Kassani, P.H., Lu, F., Le Guen, Y., Belloy, M.E., He, Z.: Deep neural networks with controlled variable selection for the identification of putative causal genetic variants. Nat. Mach. Intell. 4(9), 761\u2013771 (2022)","journal-title":"Nat. Mach. Intell."},{"key":"9_CR24","first-page":"1273","volume":"16","author":"C Leng","year":"2006","unstructured":"Leng, C., Lin, Y., Wahba, G.: A note on the lasso and related procedures in model selection. Statistica Sinica 16, 1273\u20131284 (2006)","journal-title":"Statistica Sinica"},{"issue":"2","key":"9_CR25","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1093\/biostatistics\/kxaa038","volume":"23","author":"R Li","year":"2022","unstructured":"Li, R., et al.: Fast lasso method for large-scale and ultrahigh-dimensional cox model with applications to UK biobank. Biostatistics 23(2), 522\u2013540 (2022)","journal-title":"Biostatistics"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Tsai, C.H., Lee, C.P., Lin, C.J.: Large-scale logistic regression and linear support vector machines using spark. In: BIGDATA 2014, pp. 519\u2013528 (2014)","DOI":"10.1109\/BigData.2014.7004269"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Lu, F., Raff, E., Holt, J.: A coreset learning reality check. In: AAAI, vol.\u00a037, pp. 8940\u20138948 (2023)","DOI":"10.1609\/aaai.v37i7.26074"},{"key":"9_CR28","unstructured":"Mcdonald, R., Mohri, M., Silberman, N., Walker, D., Mann, G.: Efficient large-scale distributed training of conditional maximum entropy models. In: NIPS, vol. 22 (2009)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Raff, E., Sylvester, J.: Linear models with many cores and CPUs: a stochastic atomic update scheme. In: BIGDATA, pp. 65\u201373 (2018)","DOI":"10.1109\/BigData.2018.8622172"},{"key":"9_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11416-016-0283-1","volume":"14","author":"E Raff","year":"2018","unstructured":"Raff, E., et al.: An investigation of byte N-gram features for malware classification. J. Comput. Virol. Hacking Tech. 14, 1\u201320 (2018)","journal-title":"J. Comput. Virol. Hacking Tech."},{"key":"9_CR31","unstructured":"Recht, B., Re, C., Wright, S., Niu, F.: Hogwild!: a lock-free approach to parallelizing stochastic gradient descent. In: NIPS, vol. 24 (2011)"},{"issue":"1","key":"9_CR32","first-page":"2657","volume":"17","author":"P Richt\u00e1rik","year":"2016","unstructured":"Richt\u00e1rik, P., Tak\u00e1\u010d, M.: Distributed coordinate descent method for learning with big data. J. Mach. Learn. Res. 17(1), 2657\u20132681 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"9_CR33","first-page":"379","volume":"5","author":"JD Rosenblatt","year":"2016","unstructured":"Rosenblatt, J.D., Nadler, B.: On the optimality of averaging in distributed statistical learning. Inf. Inference 5(4), 379\u2013404 (2016)","journal-title":"Inf. Inference"},{"issue":"2","key":"9_CR34","doi-asserted-by":"publisher","first-page":"26","DOI":"10.21105\/joss.00026","volume":"1","author":"C Sanderson","year":"2016","unstructured":"Sanderson, C., Curtin, R.: Armadillo: a template-based C++ library for linear algebra. J. Open Source Softw. 1(2), 26 (2016)","journal-title":"J. Open Source Softw."},{"key":"9_CR35","unstructured":"Shamir, O., Srebro, N., Zhang, T.: Communication-efficient distributed optimization using an approximate newton-type method. In: ICML, pp. 1000\u20131008 (2014)"},{"key":"9_CR36","first-page":"230","volume":"18","author":"V Smith","year":"2018","unstructured":"Smith, V., Forte, S., Chenxin, M., Tak\u00e1\u010d, M., Jordan, M.I., Jaggi, M.: CoCoA: a general framework for communication-efficient distributed optimization. JMLR 18, 230 (2018)","journal-title":"JMLR"},{"key":"9_CR37","unstructured":"Smith, V., Forte, S., Jordan, M.I., Jaggi, M.: L1-regularized distributed optimization: a communication-efficient primal-dual framework. arXiv preprint arXiv:1512.04011 (2015)"},{"key":"9_CR38","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/978-3-319-26123-2_24","volume-title":"Analysis of Images, Social Networks and Texts","author":"I Trofimov","year":"2015","unstructured":"Trofimov, I., Genkin, A.: Distributed coordinate descent for L1-regularized logistic regression. In: Khachay, M.Y., Konstantinova, N., Panchenko, A., Ignatov, D.I., Labunets, V.G. (eds.) AIST 2015. CCIS, vol. 542, pp. 243\u2013254. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-26123-2_24"},{"key":"9_CR39","unstructured":"Wang, J., Kolar, M., Srebro, N., Zhang, T.: Efficient distributed learning with sparsity. In: ICML, pp. 3636\u20133645 (2017)"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Yang, S., Yuan, H., Zhang, X., Wang, M., Zhang, H., Wang, H.: Conversational dueling bandits in generalized linear models (2024)","DOI":"10.1145\/3637528.3671892"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Yuan, G.X., Ho, C.H., Lin, C.J.: An improved GLMnet for L1-regularized logistic regression. In: KDD 2011, pp. 33\u201341 (2011)","DOI":"10.1145\/2020408.2020421"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, Y., Ma, Y., Chen, B.C., Zhang, L., Agarwal, D.: GLMIX: generalized linear mixed models for large-scale response prediction. In: KDD 2016, pp. 363\u2013372 (2016)","DOI":"10.1145\/2939672.2939684"},{"key":"9_CR43","unstructured":"Zhang, Y., Duchi, J., Wainwright, M.: Divide and conquer kernel ridge regression. In: COLT, pp. 592\u2013617 (2013)"},{"key":"9_CR44","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-319-18032-8_54","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Y Zhuang","year":"2015","unstructured":"Zhuang, Y., Chin, W.-S., Juan, Y.-C., Lin, C.-J.: Distributed newton methods for regularized logistic regression. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015. LNCS (LNAI), vol. 9078, pp. 690\u2013703. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18032-8_54"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Juan, Y., Yuan, G.X., Lin, C.J.: Naive parallelization of coordinate descent methods and an application on multi-core L1-regularized classification. In: CIKM 2018, pp. 1103\u20131112 (2018)","DOI":"10.1145\/3269206.3271687"},{"issue":"476","key":"9_CR46","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1198\/016214506000000735","volume":"101","author":"H Zou","year":"2006","unstructured":"Zou, H.: The adaptive lasso and its oracle properties. J. Am. Stat. Assoc. 101(476), 1418\u20131429 (2006)","journal-title":"J. Am. Stat. Assoc."},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Royal Stat. Soc. Series B: Stat. Methodol. 67(2), 301\u2013320 (2005)","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06096-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:25:17Z","timestamp":1777631117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06096-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"ISBN":["9783032060952","9783032060969"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06096-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"27 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}