{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:25:51Z","timestamp":1776889551877,"version":"3.51.2"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030676636","type":"print"},{"value":"9783030676643","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-67664-3_4","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T07:06:46Z","timestamp":1614150406000},"page":"57-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Orthant Based Proximal Stochastic Gradient Method for $$\\ell _1$$-Regularized Optimization"],"prefix":"10.1007","author":[{"given":"Tianyi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Andrew, G., Gao, J.: Scalable training of $$l_1$$-regularized log-linear models. In: Proceedings of the 24th International Conference on Machine Learning, pp. 33\u201340. ACM (2007)","DOI":"10.1145\/1273496.1273501"},{"issue":"1","key":"4_CR2","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1137\/080716542","volume":"2","author":"A Beck","year":"2009","unstructured":"Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183\u2013202 (2009)","journal-title":"SIAM J. Imaging Sci."},{"key":"4_CR3","volume-title":"Applied Mathematical Programming","author":"S Bradley","year":"1977","unstructured":"Bradley, S., Hax, A., Magnanti, T.: Applied Mathematical Programming. Addison-Wesley, Boston (1977)"},{"key":"4_CR4","unstructured":"Chen, T.: A Fast Reduced-Space Algorithmic Framework for Sparse Optimization. Ph.D. thesis, Johns Hopkins University (2018)"},{"issue":"3","key":"4_CR5","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1137\/16M1062259","volume":"27","author":"T Chen","year":"2017","unstructured":"Chen, T., Curtis, F.E., Robinson, D.P.: A reduced-space algorithm for minimizing $$\\ell _1$$-regularized convex functions. SIAM J. Optim. 27(3), 1583\u20131610 (2017)","journal-title":"SIAM J. Optim."},{"key":"4_CR6","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1080\/10556788.2017.1415336","volume":"33","author":"T Chen","year":"2018","unstructured":"Chen, T., Curtis, F.E., Robinson, D.P.: Farsa for $$\\ell _1$$-regularized convex optimization: local convergence and numerical experience. Optim. Methods Softw. 33, 396\u2013415 (2018)","journal-title":"Optim. Methods Softw."},{"key":"4_CR7","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T.: A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)"},{"key":"4_CR8","unstructured":"Defazio, A., Bottou, L.: On the ineffectiveness of variance reduced optimization for deep learning. In: Advances in Neural Information Processing Systems (2019)"},{"key":"4_CR9","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198772101.001.0001","volume-title":"Optimization in Economic Theory","author":"AK Dixit","year":"1990","unstructured":"Dixit, A.K.: Optimization in Economic Theory. Oxford University Press on Demand, Oxford (1990)"},{"key":"4_CR10","first-page":"2899","volume":"10","author":"J Duchi","year":"2009","unstructured":"Duchi, J., Singer, Y.: Efficient online and batch learning using forward backward splitting. J. Mach. Learn. Res. 10, 2899\u20132934 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR11","unstructured":"Ge, R., Huang, F., Jin, C., Yuan, Y.: Escaping from saddle points\u2013online stochastic gradient for tensor decomposition. In: Conference on Learning Theory, pp. 797\u2013842 (2015)"},{"key":"4_CR12","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR14","unstructured":"Howard, A.G., et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"4_CR15","first-page":"315","volume":"26","author":"R Johnson","year":"2013","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. Adv. Neural Inf. Process. Syst. 26, 315\u2013323 (2013)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Keskar, N.S., Nocedal, J., Oztoprak, F., Waechter, A.: A second-order method for convex $$\\ell _1$$-regularized optimization with active set prediction. arXiv preprint arXiv:1505.04315 (2015)","DOI":"10.1080\/10556788.2016.1138222"},{"key":"4_CR17","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master\u2019s thesis, Department of Computer Science, University of Toronto (2009)"},{"key":"4_CR18","unstructured":"Lee, J., Sun, Y., Saunders, M.: Proximal newton-type methods for convex optimization. In: Advances in Neural Information Processing Systems, pp. 836\u2013844 (2012)"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10107-007-0149-x","volume":"120","author":"Y Nesterov","year":"2009","unstructured":"Nesterov, Y.: Primal-dual subgradient methods for convex problems. Math. Program. 120, 221\u2013259 (2009). https:\/\/doi.org\/10.1007\/s10107-007-0149-x","journal-title":"Math. Program."},{"key":"4_CR20","unstructured":"Riezler, S., Vasserman, A.: Incremental feature selection and l1 regularization for relaxed maximum-entropy modeling. In: Empirical Methods in Natural Language Processing (2004)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Sra, S.: Fast projections onto $$\\ell _{1, q}$$-norm balls for grouped feature selection. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases (2011)","DOI":"10.1007\/978-3-642-23808-6_20"},{"issue":"1","key":"4_CR22","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani, R.: Regression shrinkage and selection via the lasso. J. Roy. Stat. Soc.: Ser. B (Methodol.) 58(1), 267\u2013288 (1996)","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"key":"4_CR23","volume-title":"Solution of Ill-Posed Problems","author":"N Tikhonov","year":"1977","unstructured":"Tikhonov, N., Arsenin, Y.: Solution of Ill-Posed Problems. Winston and Sons, Washington, D.C. (1977)"},{"key":"4_CR24","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms (2017)"},{"key":"4_CR25","first-page":"2543","volume":"11","author":"L Xiao","year":"2010","unstructured":"Xiao, L.: Dual averaging methods for regularized stochastic learning and online optimization. J. Mach. Learn. Res. 11, 2543\u20132596 (2010)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"4_CR26","doi-asserted-by":"publisher","first-page":"2057","DOI":"10.1137\/140961791","volume":"24","author":"L Xiao","year":"2014","unstructured":"Xiao, L., Zhang, T.: A proximal stochastic gradient method with progressive variance reduction. SIAM J. Optim. 24(4), 2057\u20132075 (2014)","journal-title":"SIAM J. Optim."},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Yang, M., Milzarek, A., Wen, Z., Zhang, T.: A stochastic extra-step quasi-newton method for nonsmooth nonconvex optimization. arXiv preprint arXiv:1910.09373 (2019)","DOI":"10.1137\/18M1181249"},{"issue":"1","key":"4_CR28","first-page":"1999","volume":"13","author":"GX Yuan","year":"2012","unstructured":"Yuan, G.X., Ho, C.H., Lin, C.J.: An improved GLMNET for l1-regularized logistic regression. J. Mach. Learn. Res. 13(1), 1999\u20132030 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR29","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)"},{"key":"4_CR30","unstructured":"Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557 (2013)"},{"key":"4_CR31","unstructured":"Zhong, K., Song, Z., Jain, P., Bartlett, P.L., Dhillon, I.S.: Recovery guarantees for one-hidden-layer neural networks. In: International Conference on Machine Learning (2017)"},{"key":"4_CR32","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Roy. Stat. Soci. B (Stat. Methodol.) 67, 301\u2013320 (2005)","journal-title":"J. Roy. Stat. Soci. B (Stat. Methodol.)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67664-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:03:52Z","timestamp":1740351832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67664-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030676636","9783030676643"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67664-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","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":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd2020.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"945","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":"195","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":"21% - 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":"4,5","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":"4,4","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)"}},{"value":"The conference took place virtually due to the COVID-19 pandemic","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}