{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:09:36Z","timestamp":1765544976597,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3672038","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"2037-2047","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["High-Dimensional Distributed Sparse Classification with Scalable Communication-Efficient Global Updates"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1026-5734","authenticated-orcid":false,"given":"Fred","family":"Lu","sequence":"first","affiliation":[{"name":"Booz Allen Hamilton & University of Maryland, Baltimore County, McLean, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9903-8214","authenticated-orcid":false,"given":"Ryan R.","family":"Curtin","sequence":"additional","affiliation":[{"name":"Booz Allen Hamilton, McLean, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9900-1972","authenticated-orcid":false,"given":"Edward","family":"Raff","sequence":"additional","affiliation":[{"name":"Booz Allen Hamilton & University of Maryland, Baltimore County, McLean, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2413-9368","authenticated-orcid":false,"given":"Francis","family":"Ferraro","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, Baltimore, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6368-8696","authenticated-orcid":false,"given":"James","family":"Holt","sequence":"additional","affiliation":[{"name":"Laboratory for Physical Sciences, College Park, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Ember: an open dataset for training static pe malware machine learning models. arXiv preprint arXiv:1804.04637","author":"Anderson Hyrum S","year":"2018","unstructured":"Hyrum S Anderson and Phil Roth. 2018. Ember: an open dataset for training static pe malware machine learning models. arXiv preprint arXiv:1804.04637 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2_1","DOI":"10.1145\/1273496.1273501"},{"doi-asserted-by":"crossref","unstructured":"Stephen Boyd Neal Parikh Eric Chu Borja Peleato Jonathan Eckstein et al. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends\u00ae in Machine learning Vol. 3 1 (2011) 1--122.","key":"e_1_3_2_2_3_1","DOI":"10.1561\/2200000016"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_4_1","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_3_2_2_5_1","volume-title":"A split-and-conquer approach for analysis of extraordinarily large data. Statistica Sinica","author":"Chen Xueying","year":"2014","unstructured":"Xueying Chen and Min-ge Xie. 2014. A split-and-conquer approach for analysis of extraordinarily large data. Statistica Sinica (2014), 1655--1684."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_6_1","DOI":"10.21105\/joss.05026"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the 23rd International Conference on Artifical Intelligence and Statistics (AISTATS","author":"Curtin Ryan R.","year":"2020","unstructured":"Ryan R. Curtin, Sungjin Im, Benjamin Moseley, Kirk Pruhs, and Alireza Samadian. 2020. Unconditional Coreset for Regularized Loss Minimization. In Proceedings of the 23rd International Conference on Artifical Intelligence and Statistics (AISTATS 2020). 482--492."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_8_1","DOI":"10.1080\/01621459.2021.1969238"},{"key":"e_1_3_2_2_9_1","volume-title":"LIBLINEAR: A library for large linear classification. the Journal of machine Learning research","author":"Fan Rong-En","year":"2008","unstructured":"Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. LIBLINEAR: A library for large linear classification. the Journal of machine Learning research, Vol. 9 (2008), 1871--1874."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_10_1","DOI":"10.18637\/jss.v033.i01"},{"key":"e_1_3_2_2_11_1","volume-title":"A field guide to forward-backward splitting with a FASTA implementation. arXiv preprint arXiv:1411.3406","author":"Goldstein Tom","year":"2014","unstructured":"Tom Goldstein, Christoph Studer, and Richard Baraniuk. 2014. A field guide to forward-backward splitting with a FASTA implementation. arXiv preprint arXiv:1411.3406 (2014)."},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Machine Learning. PMLR, 289--297","author":"Gopal Siddharth","year":"2013","unstructured":"Siddharth Gopal and Yiming Yang. 2013. Distributed training of large-scale logistic models. In International Conference on Machine Learning. PMLR, 289--297."},{"volume-title":"Statistical learning with sparsity: the lasso and generalizations","author":"Hastie Trevor","unstructured":"Trevor Hastie, Robert Tibshirani, and Martin Wainwright. 2015. Statistical learning with sparsity: the lasso and generalizations. CRC press.","key":"e_1_3_2_2_13_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_14_1","DOI":"10.1007\/978-3-030-46147-8_12"},{"unstructured":"Michael I Jordan Jason D Lee and Yun Yang. 2018. Communication-efficient distributed statistical inference. J. Amer. Statist. Assoc. (2018).","key":"e_1_3_2_2_15_1"},{"unstructured":"Amol Khanna Fred Lu and Edward Raff. 2023. The Challenge of Differentially Private Screening Rules. In Submitted to SIGIR '23.","key":"e_1_3_2_2_16_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_17_1","DOI":"10.1145\/3605764.3623910"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_18_1","DOI":"10.1109\/SaTML59370.2024.00012"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_19_1","DOI":"10.5555\/3122009.3122014"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_20_1","DOI":"10.1137\/130921428"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1109\/BigData.2014.7004269"},{"key":"e_1_3_2_2_22_1","volume-title":"Distributed estimation, information loss and exponential families. Advances in neural information processing systems","author":"Liu Qiang","year":"2014","unstructured":"Qiang Liu and Alexander T Ihler. 2014. Distributed estimation, information loss and exponential families. Advances in neural information processing systems, Vol. 27 (2014)."},{"unstructured":"Fred Lu Ryan R. Curtin Edward Raff Francis Ferraro and James Holt. 2024. Optimizing the Optimal Weighted Average: Efficient Distributed Sparse Classification. arxiv: 2406.01753 [cs.LG]","key":"e_1_3_2_2_23_1"},{"key":"e_1_3_2_2_24_1","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Lu Fred","year":"2022","unstructured":"Fred Lu, Joseph Munoz, Maya Fuchs, Tyler LeBlond, Elliott Zaresky-Williams, Edward Raff, Francis Ferraro, and Brian Testa. 2022. A General Framework for Auditing Differentially Private Machine Learning. In Advances in Neural Information Processing Systems, Vol. 35. Curran Associates, Inc., 4165--4176."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_25_1","DOI":"10.1609\/aaai.v37i7.26074"},{"doi-asserted-by":"crossref","unstructured":"Sahand N Negahban Pradeep Ravikumar Martin J Wainwright and Bin Yu. 2012. A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers. (2012).","key":"e_1_3_2_2_26_1","DOI":"10.1214\/12-STS400"},{"key":"e_1_3_2_2_27_1","first-page":"1","article-title":"JSAT: Java Statistical Analysis Tool, a Library for Machine Learning","volume":"18","author":"Raff Edward","year":"2017","unstructured":"Edward Raff. 2017. JSAT: Java Statistical Analysis Tool, a Library for Machine Learning. Journal of Machine Learning Research, Vol. 18, 23 (2017), 1--5. http:\/\/jmlr.org\/papers\/v18\/16--131.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of KDD 2019 Workshop on Learning and Mining for Cybersecurity (LEMINCS'19)","author":"Raff Edward","year":"2019","unstructured":"Edward Raff, William Fleming, Richard Zak, Hyrum Anderson, Bill Finlayson, Charles K. Nicholas, Mark Mclean, William Fleming, Charles K. Nicholas, Richard Zak, and Mark Mclean. 2019. KiloGrams: Very Large N-Grams for Malware Classification. In Proceedings of KDD 2019 Workshop on Learning and Mining for Cybersecurity (LEMINCS'19). https:\/\/arxiv.org\/abs\/1908.00200"},{"key":"e_1_3_2_2_29_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=SuvDnzrKCo","author":"Raff Edward","year":"2023","unstructured":"Edward Raff, Amol Ashish Khanna, and Fred Lu. 2023. Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=SuvDnzrKCo"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1109\/BigData.2018.8622043"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_31_1","DOI":"10.1145\/3209280.3229085"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_32_1","DOI":"10.1109\/BigData.2018.8622172"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1007\/s11416-016-0283--1"},{"key":"e_1_3_2_2_34_1","volume-title":"A lock-free approach to parallelizing stochastic gradient descent. Advances in neural information processing systems","author":"Recht Benjamin","year":"2011","unstructured":"Benjamin Recht, Christopher Re, Stephen Wright, and Feng Niu. 2011. Hogwild!: A lock-free approach to parallelizing stochastic gradient descent. Advances in neural information processing systems, Vol. 24 (2011)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_35_1","DOI":"10.5555\/2946645.3007028"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_36_1","DOI":"10.1093\/imaiai\/iaw013"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.21105\/joss.00026"},{"key":"e_1_3_2_2_38_1","volume-title":"International conference on machine learning. PMLR, 1000--1008","author":"Shamir Ohad","year":"2014","unstructured":"Ohad Shamir, Nati Srebro, and Tong Zhang. 2014. Communication-efficient distributed optimization using an approximate newton-type method. In International conference on machine learning. PMLR, 1000--1008."},{"key":"e_1_3_2_2_39_1","volume-title":"Social Networks and Texts: 4th International Conference, AIST 2015","author":"Trofimov Ilya","year":"2015","unstructured":"Ilya Trofimov and Alexander Genkin. 2015. Distributed coordinate descent for l1-regularized logistic regression. In Analysis of Images, Social Networks and Texts: 4th International Conference, AIST 2015, Yekaterinburg, Russia, April 9--11, 2015, Revised Selected Papers 4. Springer, 243--254."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_40_1","DOI":"10.1007\/s10107-007-0170-0"},{"key":"e_1_3_2_2_41_1","volume-title":"International conference on machine learning. PMLR, 3636--3645","author":"Wang Jialei","year":"2017","unstructured":"Jialei Wang, Mladen Kolar, Nathan Srebro, and Tong Zhang. 2017. Efficient distributed learning with sparsity. In International conference on machine learning. PMLR, 3636--3645."},{"key":"e_1_3_2_2_42_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Wang Shusen","year":"2018","unstructured":"Shusen Wang, Fred Roosta, Peng Xu, and Michael W Mahoney. 2018. Giant: Globally improved approximate newton method for distributed optimization. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_43_1","DOI":"10.1145\/2020408.2020421"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_44_1","DOI":"10.1109\/MALWARE.2017.8323963"},{"key":"e_1_3_2_2_45_1","volume-title":"Communication-efficient algorithms for statistical optimization. Advances in neural information processing systems","author":"Zhang Yuchen","year":"2012","unstructured":"Yuchen Zhang, Martin J Wainwright, and John C Duchi. 2012. Communication-efficient algorithms for statistical optimization. Advances in neural information processing systems, Vol. 25 (2012)."},{"key":"e_1_3_2_2_46_1","volume-title":"Communication-efficient distributed optimization of self-concordant empirical loss. Large-Scale and Distributed Optimization","author":"Zhang Yuchen","year":"2018","unstructured":"Yuchen Zhang and Lin Xiao. 2018. Communication-efficient distributed optimization of self-concordant empirical loss. Large-Scale and Distributed Optimization (2018), 289--341."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_47_1","DOI":"10.1007\/978-3-319-18032-8_54"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_48_1","DOI":"10.1145\/3269206.3271687"},{"key":"e_1_3_2_2_49_1","volume-title":"Parallelized stochastic gradient descent. Advances in neural information processing systems","author":"Zinkevich Martin","year":"2010","unstructured":"Martin Zinkevich, Markus Weimer, Lihong Li, and Alex Smola. 2010. Parallelized stochastic gradient descent. Advances in neural information processing systems, Vol. 23 (2010)."}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"acronym":"KDD '24","name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain"},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3672038","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3672038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:06Z","timestamp":1750291566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3672038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":49,"alternative-id":["10.1145\/3637528.3672038","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3672038","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}