{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T22:23:13Z","timestamp":1778106193798,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,6,24]],"date-time":"2012-06-24T00:00:00Z","timestamp":1340496000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Math. Program."],"published-print":{"date-parts":[[2012,8]]},"DOI":"10.1007\/s10107-012-0572-5","type":"journal-article","created":{"date-parts":[[2012,6,23]],"date-time":"2012-06-23T00:04:25Z","timestamp":1340409865000},"page":"127-155","source":"Crossref","is-referenced-by-count":262,"title":["Sample size selection in optimization methods for machine learning"],"prefix":"10.1007","volume":"134","author":[{"given":"Richard H.","family":"Byrd","sequence":"first","affiliation":[]},{"given":"Gillian M.","family":"Chin","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Nocedal","sequence":"additional","affiliation":[]},{"given":"Yuchen","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,6,24]]},"reference":[{"key":"572_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Duchi, J.: Distributed delayed stochastic optimization. Arxiv preprint arXiv:1104.5525 (2011)","DOI":"10.1109\/CDC.2012.6426626"},{"key":"572_CR2","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":"572_CR3","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/s10287-005-0044-y","volume":"3","author":"F. Bastin","year":"2006","unstructured":"Bastin F., Cirillo C., Toint P.L.: An adaptive monte carlo algorithm for computing mixed logit estimators. Comput. Manag. Sci. 3(1), 55\u201379 (2006)","journal-title":"Comput. Manag. Sci."},{"issue":"1","key":"572_CR4","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. Imaging Sci. 2(1), 183\u2013202 (2009)","journal-title":"SIAM J. Imaging Sci."},{"key":"572_CR5","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/TAC.1976.1101194","volume":"AC-21","author":"D.P. Bertsekas","year":"1976","unstructured":"Bertsekas D.P.: On the Goldstein-Levitin-Poljak gradient projection method. IEEE Trans. Autom. Control AC-21, 174\u2013184 (1976)","journal-title":"IEEE Trans. Autom. Control"},{"key":"572_CR6","first-page":"161","volume-title":"Advances in Neural Information Processing Systems, vol. 20","author":"L. Bottou","year":"2008","unstructured":"Bottou L., Bousquet O.: The tradeoffs of large scale learning. In: Platt, J., Koller, D., Singer, Y., Roweis, S. (eds) Advances in Neural Information Processing Systems, vol. 20, pp. 161\u2013168. MIT Press, Cambridge, MA (2008)"},{"key":"572_CR7","doi-asserted-by":"crossref","unstructured":"Byrd, R., Chin, G.M., Neveitt, W., Nocedal, J.: On the use of stochastic Hessian information in unconstrained optimization. SIAM J. Optim. 21(3), 977\u2013995 (2011)","DOI":"10.1137\/10079923X"},{"issue":"2","key":"572_CR8","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1137\/0728030","volume":"28","author":"A.R. Conn","year":"1991","unstructured":"Conn A.R., Gould N.I.M., Toint P.L.: A globally convergent augmented Lagrangian algorithm for optimization with general constraints and simple bounds. SIAM J. Numer. Anal. 28(2), 545\u2013572 (1991)","journal-title":"SIAM J. Numer. Anal."},{"issue":"1","key":"572_CR9","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s00211-004-0569-y","volume":"100","author":"Y. Dai","year":"2005","unstructured":"Dai Y., Fletcher R.: Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming. Numerische Mathematik 100(1), 21\u201347 (2005)","journal-title":"Numerische Mathematik"},{"key":"572_CR10","unstructured":"Dekel, O., Gilad-Bachrach, R., Shamir, O., Xiao, L.: Optimal distributed online prediction using mini-batches. Arxiv preprint arXiv:1012.1367 (2010)"},{"issue":"1\u20132","key":"572_CR11","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s10107-007-0164-y","volume":"117","author":"G. Deng","year":"2009","unstructured":"Deng G., Ferris M.C.: Variable-number sample-path optimization. Math. Program. 117(1\u20132), 81\u2013109 (2009)","journal-title":"Math. Program."},{"issue":"3","key":"572_CR12","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1109\/18.382009","volume":"41","author":"D. Donoho","year":"1995","unstructured":"Donoho D.: De-noising by soft-thresholding. Inf. Theory IEEE Trans. 41(3), 613\u2013627 (1995)","journal-title":"Inf. Theory IEEE Trans."},{"key":"572_CR13","unstructured":"Duchi, J., Shalev-Shwartz, S., Singer, Y., Tewari, A.: Composite objective mirror descent. In: Proceedings of the Twenty Third Annual Conference on Computational Learning Theory. Citeseer (2010)"},{"key":"572_CR14","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."},{"issue":"4","key":"572_CR15","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1109\/JSTSP.2007.910281","volume":"1","author":"M. Figueiredo","year":"2007","unstructured":"Figueiredo M., Nowak R., Wright S.: Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems. IEEE J. Sel. Top. Signal Process. 1(4), 586\u2013597 (2007)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"572_CR16","volume-title":"Mathematical Statistics","author":"J.E. Freund","year":"1962","unstructured":"Freund J.E.: Mathematical Statistics. Prentice Hall, Englewood Cliffs, NJ (1962)"},{"key":"572_CR17","unstructured":"Friedlander, M., Schmidt, M.: Hybrid deterministic-stochastic methods for data fitting. Arxiv preprint arXiv:1104.2373 (2011)"},{"issue":"2","key":"572_CR18","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1137\/050635225","volume":"17","author":"W.W. Hager","year":"2007","unstructured":"Hager W.W., Zhang H.: A new active set\u00a0algorithm for box constrained optimization. SIOPT 17(2), 526\u2013557 (2007)","journal-title":"SIOPT"},{"issue":"2","key":"572_CR19","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1145\/858481.858483","volume":"13","author":"T. Homem-de-Mello","year":"2003","unstructured":"Homem-de-Mello T.: Variable-sample methods for stochastic optimization. ACM Trans. Model. Comput. Simul. 13(2), 108\u2013133 (2003)","journal-title":"ACM Trans. Model. Comput. Simul."},{"issue":"2","key":"572_CR20","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1137\/S1052623499363220","volume":"12","author":"A.J. Kleywegt","year":"2001","unstructured":"Kleywegt A.J., Shapiro A., Homem-de-Mello T.: The sample average approximation method for stochastic discrete optimization. SIAM J. Optim. 12(2), 479\u2013502 (2001)","journal-title":"SIAM J. Optim."},{"issue":"4","key":"572_CR21","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1137\/S1052623498345075","volume":"9","author":"C. Lin","year":"1999","unstructured":"Lin C., Mor\u00e9 J. et\u00a0al.: Newton\u2019s method for large bound-constrained optimization problems. SIAM J. Optim. 9(4), 1100\u20131127 (1999)","journal-title":"SIAM J. Optim."},{"key":"572_CR22","unstructured":"Martens, J.: Deep learning via Hessian-free optimization. In: Proceedings of the 27th International Conference on Machine Learning (ICML) (2010)"},{"issue":"1","key":"572_CR23","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. 120(1), 221\u2013259 (2009). doi: 10.1007\/s10107-007-0149-x","journal-title":"Math. Program."},{"key":"572_CR24","unstructured":"Niu, F., Recht, B., R\u00e9, C., Wright, S.: Hogwild!: a lock-free approach to parallelizing stochastic gradient descent. Arxiv preprint arXiv:1106.5730 (2011)"},{"key":"572_CR25","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"B. Polyak","year":"1992","unstructured":"Polyak B., Juditsky A.: Acceleration of stochastic approximation by averaging. SIAM J. Control Optim. 30, 838 (1992)","journal-title":"SIAM J. Control Optim."},{"key":"572_CR26","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/0041-5553(69)90035-4","volume":"9","author":"B.T. Polyak","year":"1969","unstructured":"Polyak B.T.: The conjugate gradient method in extremal problems. USSR Comput. Math. Math. Phys. 9, 94\u2013112 (1969)","journal-title":"USSR Comput. Math. Math. Phys."},{"issue":"3","key":"572_CR27","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H. Robbins","year":"1951","unstructured":"Robbins H., Monro S.: A stochastic approximation method. Ann. Math. Stat. 22(3), 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"572_CR28","first-page":"301","volume":"81","author":"A. Shapiro","year":"1998","unstructured":"Shapiro A., Homem-de-Mello T.: A simulation-based approach to two-stage stochastic programming with recourse. Math. Program. 81, 301\u2013325 (1998)","journal-title":"Math. Program."},{"issue":"1","key":"572_CR29","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1137\/S1052623498349541","volume":"11","author":"A. Shapiro","year":"2000","unstructured":"Shapiro A., Homem-de-Mello T.: On the rate of convergence of optimal solutions of monte carlo approximations of stochastic programs. SIAM J. Optim. 11(1), 70\u201386 (2000)","journal-title":"SIAM J. Optim."},{"issue":"3","key":"572_CR30","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1287\/moor.21.3.615","volume":"21","author":"A. Shapiro","year":"1996","unstructured":"Shapiro A., Wardi Y.: Convergence of stochastic algorithms. Math. Oper. Res. 21(3), 615\u2013628 (1996)","journal-title":"Math. Oper. Res."},{"key":"572_CR31","doi-asserted-by":"crossref","unstructured":"Vishwanathan, S., Schraudolph, N., Schmidt, M., Murphy, K.: Accelerated training of conditional random fields with stochastic gradient methods. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 969\u2013976. ACM (2006)","DOI":"10.1145\/1143844.1143966"},{"key":"572_CR32","unstructured":"Wright, S.: Accelerated block-coordinate relaxation for regularized optimization. Tech. rep., Computer Science Department, University of Wisconsin (2010)"},{"issue":"7","key":"572_CR33","doi-asserted-by":"crossref","first-page":"2479","DOI":"10.1109\/TSP.2009.2016892","volume":"57","author":"S. Wright","year":"2009","unstructured":"Wright S., Nowak R., Figueiredo M.: Sparse reconstruction by separable approximation. Signal Process. IEEE Trans. 57(7), 2479\u20132493 (2009)","journal-title":"Signal Process. IEEE Trans."},{"key":"572_CR34","first-page":"2543","volume":"9999","author":"L. Xiao","year":"2010","unstructured":"Xiao L.: Dual averaging methods for regularized stochastic learning and online optimization. J. Mach. Learn. Res. 9999, 2543\u20132596 (2010)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Mathematical Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10107-012-0572-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10107-012-0572-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10107-012-0572-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,30]],"date-time":"2019-06-30T02:47:14Z","timestamp":1561862834000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10107-012-0572-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,24]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,8]]}},"alternative-id":["572"],"URL":"https:\/\/doi.org\/10.1007\/s10107-012-0572-5","relation":{},"ISSN":["0025-5610","1436-4646"],"issn-type":[{"value":"0025-5610","type":"print"},{"value":"1436-4646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,24]]}}}