{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T02:36:16Z","timestamp":1777430176862,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2014,4,22]],"date-time":"2014-04-22T00:00:00Z","timestamp":1398124800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1007\/s11432-014-5082-z","type":"journal-article","created":{"date-parts":[[2014,4,21]],"date-time":"2014-04-21T01:50:04Z","timestamp":1398045004000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Feature-aware regularization for sparse online learning"],"prefix":"10.1007","volume":"57","author":[{"given":"Hidekazu","family":"Oiwa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shin","family":"Matsushima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Nakagawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,4,22]]},"reference":[{"key":"5082_CR1","first-page":"833","volume-title":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","author":"H-F Yu","year":"2010","unstructured":"Yu H-F, Hsieh C-J, Chang K-W, et al. Large linear classification when data cannot fit in memory. In: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: ACM, 2010. 833\u2013842"},{"key":"5082_CR2","first-page":"2899","volume":"10","author":"J Duchi","year":"2009","unstructured":"Duchi J, Singer Y. Effcient online and batch learning using forward backward splitting. J Mach Learn Res, 2009, 10: 2899\u20132934","journal-title":"J Mach Learn Res"},{"key":"5082_CR3","first-page":"14","volume-title":"23rd International Conference on Learning Theory, Haifa","author":"J Duchi","year":"2010","unstructured":"Duchi J, Shalev-Shwartz S, Singer Y, et al. Composite objective mirror descent. In: 23rd International Conference on Learning Theory, Haifa, 2010. 14\u201326"},{"key":"5082_CR4","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, 2010, 11: 2543\u20132596","journal-title":"J Mach Learn Res"},{"key":"5082_CR5","first-page":"244","volume-title":"23rd International Conference on Learning Theory, Haifa","author":"H Brendan McMahan","year":"2010","unstructured":"Brendan McMahan H, Streeter M J. Adaptive bound optimization for online convex optimization. In: 23rd International Conference on Learning Theory, Haifa, 2010. 244\u2013256"},{"key":"5082_CR6","first-page":"525","volume-title":"14th International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale","author":"H Brendan McMahan","year":"2011","unstructured":"Brendan McMahan H. Follow-the-regularized-leader and mirror descent: equivalence theorems and l1 regularization. In: 14th International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale, 2011. 525\u2013533"},{"key":"5082_CR7","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton G, Buckley C. Term-weighting approaches in automatic text retrieval. Inf Process Manage, 1988, 24: 513\u2013523","journal-title":"Inf Process Manage"},{"key":"5082_CR8","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1561\/2200000018","volume":"4","author":"S Shalev-Shwartz","year":"2012","unstructured":"Shalev-Shwartz S. Online learning and online convex optimization. Found Trends Mach Learn, 2012, 4: 107\u2013194","journal-title":"Found Trends Mach Learn"},{"key":"5082_CR9","volume-title":"Nonlinear Programming","author":"D P Bertsekas","year":"1999","unstructured":"Bertsekas D P. Nonlinear Programming. 2nd edition. Athena Scientific. 1999","edition":"2nd edition"},{"key":"5082_CR10","first-page":"928","volume-title":"20th International Conference on Machine Learning, Washington D. C.","author":"M Zinkevich","year":"2003","unstructured":"Zinkevich M. Online convex programming and generalized infinitesimal gradient ascent. In: 20th International Conference on Machine Learning, Washington D. C., 2003. 928\u2013936"},{"key":"5082_CR11","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/S0167-6377(02)00231-6","volume":"31","author":"A Beck","year":"2003","unstructured":"Beck A, Teboulle M. Mirror descent and nonlinear projected subgradient methods for convex optimization. Oper Res Lett, 2003, 31: 167\u2013175","journal-title":"Oper Res Lett"},{"key":"5082_CR12","doi-asserted-by":"crossref","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, 2009, 120: 221\u2013259","journal-title":"Math Program"},{"key":"5082_CR13","first-page":"372","volume":"27","author":"Y Nesterov","year":"1983","unstructured":"Nesterov Y. A method of solving a convex programming problem with convergence rate o(1\/k2). Sov Math Dokl, 1983, 27: 372\u2013376","journal-title":"Sov Math Dokl"},{"key":"5082_CR14","doi-asserted-by":"crossref","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 Imag Sci, 2009, 2: 183\u2013202","journal-title":"SIAM J Imag Sci"},{"key":"5082_CR15","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s10107-010-0394-2","volume":"125","author":"P Tseng","year":"2010","unstructured":"Tseng P. Approximation accuracy, gradient methods, and error bound for structured convex optimization. Math Program, 2010, 125: 263\u2013295","journal-title":"Math Program"},{"key":"5082_CR16","volume-title":"Lazy sparse stochastic gradient descent for regularized multinomial logistic regression","author":"B Carpenter","year":"2008","unstructured":"Carpenter B. Lazy sparse stochastic gradient descent for regularized multinomial logistic regression. Technical Report, Alias-i, Inc. 2008"},{"key":"5082_CR17","first-page":"777","volume":"10","author":"J Langford","year":"2009","unstructured":"Langford J, Li L H, Zhang T. Sparse online learning via truncated gradient. J Mach Learn Res, 2009, 10: 777\u2013801","journal-title":"J Mach Learn Res"},{"key":"5082_CR18","first-page":"477","volume-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP","author":"Y Tsuruoka","year":"2009","unstructured":"Tsuruoka Y, Tsujii J, Ananiadou S. Stochastic gradient descent training for l1-regularized log-linear. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Stroudsburg: Association for Computational Linguistics, 2009. 477\u2013485"},{"key":"5082_CR19","first-page":"1265","volume-title":"Advances in Neural Information Processing Systems, Vancouver","author":"S Shalev-shwartz","year":"2006","unstructured":"Shalev-shwartz S, Singer Y. Convex repeated games and fenchel duality. In: Advances in Neural Information Processing Systems, Vancouver, 2006. 1265\u20131272"},{"key":"5082_CR20","first-page":"165","volume":"13","author":"O Dekel","year":"2012","unstructured":"Dekel O, Gilad-Bachrach R, Shamir O, et al. Optimal distributed online prediction using mini-batches. J Mach Learn Res, 2012, 13: 165\u2013202","journal-title":"J Mach Learn Res"},{"key":"5082_CR21","first-page":"550","volume-title":"Advances in Neural Information Processing Systems, Vancouver","author":"J Duchi","year":"2010","unstructured":"Duchi J, Agarwal A, Wainwright M J. Distributed dual averaging in networks. In: Advances in Neural Information Processing Systems, Vancouver, 2010. 550\u2013558"},{"key":"5082_CR22","first-page":"1705","volume":"13","author":"S Lee","year":"2012","unstructured":"Lee S, Wright S J. Manifold identification in dual averaging for regularized stochastic online learning. J Mach Learn Res, 2012, 13: 1705\u20131744","journal-title":"J Mach Learn Res"},{"key":"5082_CR23","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res, 2011, 12: 2121\u20132159","journal-title":"J Mach Learn Res"},{"key":"5082_CR24","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.jcss.2004.10.016","volume":"71","author":"A Kalai","year":"2005","unstructured":"Kalai A, Vempala S. Efficient algorithms for online decision problems. J Comput Syst Sci, 2005, 71: 291\u2013307","journal-title":"J Comput Syst Sci"},{"key":"5082_CR25","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s10994-007-5014-x","volume":"69","author":"S Shalev-Shwartz","year":"2007","unstructured":"Shalev-Shwartz S, Singer Y. A primal-dual perspective of online learning algorithms. Mach Learn, 2007, 69: 115\u2013142","journal-title":"Mach Learn"},{"key":"5082_CR26","volume-title":"MIT Press","author":"S Sra","year":"2011","unstructured":"Sra S, Nowozin S, Wright S J. Optimization for Machine Learning. MIT Press, 2011"},{"key":"5082_CR27","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev, 1958, 65: 386\u2013408","journal-title":"Psychol Rev"},{"key":"5082_CR28","first-page":"551","volume":"7","author":"K Crammer","year":"2006","unstructured":"Crammer K, Dekel O, Keshet J, et al. Online passive-aggressive algorithms. J Mach Learn Res, 2006, 7: 551\u2013585","journal-title":"J Mach Learn Res"},{"key":"5082_CR29","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/1390156.1390190","volume-title":"25th international conference on Machine learning","author":"M Dredze","year":"2008","unstructured":"Dredze M, Crammer K, Pereira F. Confidence-weighted linear classification. In: 25th international conference on Machine learning. New York: ACM, 2008. 264\u2013271"},{"key":"5082_CR30","first-page":"345","volume-title":"Advances in Neural Information Processing Systems, Vancouver","author":"K Crammer","year":"2008","unstructured":"Crammer K, Fern M D, Pereira O. Exact convex confidence-weighted learning. In: Advances in Neural Information Processing Systems, Vancouver, 2008. 345\u2013352"},{"key":"5082_CR31","first-page":"1777","volume-title":"Advances in Neural Information Processing Systems, Vancouver","author":"H Narayanan","year":"2010","unstructured":"Narayanan H, Rakhlin A. Random walk approach to regret minimization. In: Advances in Neural Information Processing Systems, Vancouver, 2010. 1777\u20131785"},{"key":"5082_CR32","first-page":"343","volume-title":"Advances in Neural Information Processing Systems, Granada","author":"N Cesa-Bianchi","year":"2011","unstructured":"Cesa-Bianchi N, Shamir O. Efficient online learning via randomized rounding. In: Advances in Neural Information Processing Systems, Granada, 2011. 343\u2013351"},{"key":"5082_CR33","doi-asserted-by":"crossref","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 Statist Soc Ser B, 2005, 67: 301\u2013320","journal-title":"J Roy Statist Soc Ser B"},{"key":"5082_CR34","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1111\/j.1541-0420.2007.00843.x","volume":"64","author":"H D Bondell","year":"2008","unstructured":"Bondell H D, Reich B J. Simultaneous regression shrinkage, variable selection, and supervised clustering of predictors with oscar. Biometrics, 2008, 64: 115\u2013123","journal-title":"Biometrics"},{"key":"5082_CR35","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s10115-012-0545-2","volume":"36","author":"D J Luo","year":"2013","unstructured":"Luo D J, Ding C H Q, Huang H. Toward structural sparsity: an explicit 2\/0 approach. Knowl Inf Syst, 2013, 36: 411\u2013438","journal-title":"Knowl Inf Syst"},{"key":"5082_CR36","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1109\/TPAMI.2012.197","volume":"35","author":"X D Wu","year":"2013","unstructured":"Wu X D, Yu K, Ding W, et al. Online feature selection with streaming features. IEEE Trans Patt Anal Mach Intell, 2013, 35: 1178\u20131192","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"5082_CR37","volume-title":"Knowl Inf Syst","author":"H X Wang","year":"2013","unstructured":"Wang H X, Zheng W M. Robust sparsity-preserved learning with application to image visualization. Knowl Inf Syst, 2013. doi: 10.1007\/s10115-012-0605-7"},{"key":"5082_CR38","first-page":"575","volume-title":"IEEE 12th International Conference on Data Mining (ICDM), Brussels","author":"H Oiwa","year":"2012","unstructured":"Oiwa H, Matsushima S, Nakagawa H. Healing truncation bias: self-weighted truncation framework for dual averaging. In: IEEE 12th International Conference on Data Mining (ICDM), Brussels, 2012. 575\u2013584"},{"key":"5082_CR39","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/978-3-642-23783-6_34","volume":"6912","author":"H Oiwa","year":"2011","unstructured":"Oiwa H, Matsushima S, Nakagawa H. Frequency-aware truncated methods for sparse online learning. Lect Notes Comput Sci, 2011, 6912: 533\u2013548","journal-title":"Lect Notes Comput Sci"},{"key":"5082_CR40","volume-title":"A unified view of regularized dual averaging and mirror descent with implicit updates","author":"H Brendan McMahan","year":"2010","unstructured":"Brendan McMahan H. A unified view of regularized dual averaging and mirror descent with implicit updates. arXiv:1009.3240, 2010"},{"key":"5082_CR41","first-page":"440","volume-title":"45th Annual Meeting of the Association of Computational Linguistics, Prague","author":"J Blitzer","year":"2007","unstructured":"Blitzer J, Dredze M, Pereira F. Biographies, bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. In: 45th Annual Meeting of the Association of Computational Linguistics, Prague, 2007. 440\u2013447"},{"key":"5082_CR42","first-page":"331","volume-title":"12th International Conference on Machine Learning, Lake Tahoe","author":"K Lang","year":"1995","unstructured":"Lang K. Newsweeder: learning to filter netnews. In: 12th International Conference on Machine Learning, Lake Tahoe, 1995. 331\u2013339"},{"key":"5082_CR43","first-page":"303","volume-title":"SIAM International Conference on Data Mining, Mesa","author":"S Matsushima","year":"2010","unstructured":"Matsushima S, Shimizu N, Yoshida K, et al. Exact passive-aggressive algorithm for multiclass classification using support class. In: SIAM International Conference on Data Mining, Mesa, 2010. 303\u2013314"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-014-5082-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11432-014-5082-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-014-5082-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:32:24Z","timestamp":1648859544000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11432-014-5082-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,22]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2014,5]]}},"alternative-id":["5082"],"URL":"https:\/\/doi.org\/10.1007\/s11432-014-5082-z","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,22]]}}}