{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:02:01Z","timestamp":1763017321999},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,9,11]],"date-time":"2013-09-11T00:00:00Z","timestamp":1378857600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1007\/s10957-013-0409-2","type":"journal-article","created":{"date-parts":[[2013,9,11]],"date-time":"2013-09-11T09:05:31Z","timestamp":1378890331000},"page":"832-853","source":"Crossref","is-referenced-by-count":22,"title":["Incrementally Updated Gradient Methods for Constrained and Regularized Optimization"],"prefix":"10.1007","volume":"160","author":[{"given":"Paul","family":"Tseng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangwoon","family":"Yun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,9,11]]},"reference":[{"key":"409_CR1","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1137\/S1052623495287022","volume":"7","author":"D.P. Bertsekas","year":"1997","unstructured":"Bertsekas, D.P.: A new class of incremental gradient methods for least squares problems. SIAM J. Optim. 7, 913\u2013926 (1997)","journal-title":"SIAM J. Optim."},{"key":"409_CR2","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1080\/10556789408805582","volume":"4","author":"A.A. Gaivoronski","year":"1994","unstructured":"Gaivoronski, A.A.: Convergence properties of back-propagation for neural nets via theory of stochastic gradient methods. Part I. Optim. Methods Softw. 4, 117\u2013134 (1994)","journal-title":"Optim. Methods Softw."},{"key":"409_CR3","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1080\/10556789408805580","volume":"4","author":"Z.-Q. Luo","year":"1994","unstructured":"Luo, Z.-Q., Tseng, P.: Analysis of an approximate gradient projection method with applications to the backpropagation algorithm. Optim. Methods Softw. 4, 85\u2013101 (1994)","journal-title":"Optim. Methods Softw."},{"key":"409_CR4","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1080\/10556789408805581","volume":"4","author":"O.L. Mangasarian","year":"1994","unstructured":"Mangasarian, O.L., Solodov, M.V.: Serial and parallel backpropagation convergence via nonmonotone perturbed minimization. Optim. Methods Softw. 4, 103\u2013116 (1994)","journal-title":"Optim. Methods Softw."},{"key":"409_CR5","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1162\/neco.1989.1.4.425","volume":"1","author":"H. White","year":"1989","unstructured":"White, H.: Learning in artificial neural networks: a statistical perspective. Neural Comput. 1, 425\u2013464 (1989)","journal-title":"Neural Comput."},{"key":"409_CR6","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1080\/01621459.1989.10478865","volume":"84","author":"H. White","year":"1989","unstructured":"White, H.: Some asymptotic results for learning in single hidden-layer feedforward network models. J. Am. Stat. Assoc. 84, 1003\u20131013 (1989)","journal-title":"J. Am. Stat. Assoc."},{"key":"409_CR7","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1162\/neco.1991.3.2.226","volume":"3","author":"Z.-Q. Luo","year":"1991","unstructured":"Luo, Z.-Q.: On the convergence of the LMS algorithm with adaptive learning rate for linear feedforward networks. Neural Comput. 3, 226\u2013245 (1991)","journal-title":"Neural Comput."},{"key":"409_CR8","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1023\/A:1018366000512","volume":"11","author":"M.V. Solodov","year":"1998","unstructured":"Solodov, M.V.: Incremental gradient algorithms with stepsizes bounded away from zero. Comput. Optim. Appl. 11, 23\u201335 (1998)","journal-title":"Comput. Optim. Appl."},{"key":"409_CR9","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1080\/10556789408805583","volume":"4","author":"L. Grippo","year":"1994","unstructured":"Grippo, L.: A class of unconstrained minimization methods for neural network training. Optim. Methods Softw. 4, 135\u2013150 (1994)","journal-title":"Optim. Methods Softw."},{"key":"409_CR10","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1137\/S1052623495294797","volume":"8","author":"P. Tseng","year":"1998","unstructured":"Tseng, P.: An incremental gradient(-projection) method with momentum term and adaptive stepsize rule. SIAM J. Optim. 8, 506\u2013531 (1998)","journal-title":"SIAM J. Optim."},{"key":"409_CR11","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1137\/040615961","volume":"18","author":"D. Blatt","year":"2007","unstructured":"Blatt, D., Hero, A.O., Gauchman, H.: A convergent incremental gradient method with a constant step size. SIAM J. Optim. 18, 29\u201351 (2007)","journal-title":"SIAM J. Optim."},{"key":"409_CR12","doi-asserted-by":"crossref","first-page":"318","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel Distributed Processing\u2014Explorations in the Microstructure of Cognition","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing\u2014Explorations in the Microstructure of Cognition, pp. 318\u2013362. MIT press, Cambridge (1986)"},{"key":"409_CR13","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1162\/neco.1989.1.3.382","volume":"1","author":"G. Tesauro","year":"1989","unstructured":"Tesauro, G., He, Y., Ahmad, S.: Asymptotic convergence of back propagation. Neural Comput. 1, 382\u2013391 (1989)","journal-title":"Neural Comput."},{"key":"409_CR14","unstructured":"Werbos, P.J.: Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. Thesis, Committee on Applied Mathematics, Harvard University, Cambridge (1974)"},{"key":"409_CR15","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/5.58337","volume":"78","author":"P.J. Werbos","year":"1990","unstructured":"Werbos, P.J.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78, 1550\u20131560 (1990)","journal-title":"Proc. IEEE"},{"key":"409_CR16","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1137\/S1064827596304010","volume":"20","author":"S. Chen","year":"1999","unstructured":"Chen, S., Donoho, D., Saunders, M.: Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20, 33\u201361 (1999)","journal-title":"SIAM J. Sci. Comput."},{"key":"409_CR17","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1002\/cpa.20042","volume":"57","author":"I. Daubechies","year":"2004","unstructured":"Daubechies, I., Defrise, M., De Mol, C.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57, 1413\u20131457 (2004)","journal-title":"Commun. Pure Appl. Math."},{"key":"409_CR18","doi-asserted-by":"crossref","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\u201322 (2010)","journal-title":"J. Stat. Softw."},{"key":"409_CR19","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. R. Stat. Soc. B 58, 267\u2013288 (1996)","journal-title":"J. R. Stat. Soc. B"},{"key":"409_CR20","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s10107-007-0170-0","volume":"117","author":"P. Tseng","year":"2009","unstructured":"Tseng, P., Yun, S.: A coordinate gradient descent method for nonsmooth separable minimization. Math. Program. 117, 387\u2013423 (2009)","journal-title":"Math. Program."},{"key":"409_CR21","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."},{"key":"409_CR22","doi-asserted-by":"crossref","DOI":"10.1515\/9781400873173","volume-title":"Convex Analysis","author":"R.T. Rockafellar","year":"1970","unstructured":"Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)"},{"key":"409_CR23","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1080\/00207728108963798","volume":"12","author":"M. Fukushima","year":"1981","unstructured":"Fukushima, M., Mine, H.: A generalized proximal point algorithm for certain non-convex minimization problems. Int. J. Syst. Sci. 12, 989\u20131000 (1981)","journal-title":"Int. J. Syst. Sci."},{"key":"409_CR24","volume-title":"Parallel and Distributed Computation: Numerical Methods","author":"D.P. Bertsekas","year":"1989","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation: Numerical Methods. Prentice-Hall, Englewood Cliffs (1989)"},{"key":"409_CR25","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1137\/0801036","volume":"1","author":"P. Tseng","year":"1991","unstructured":"Tseng, P.: On the rate of convergence of a partially asynchronous gradient projection algorithm. SIAM J. Optim. 1, 603\u2013619 (1991)","journal-title":"SIAM J. Optim."},{"key":"409_CR26","doi-asserted-by":"crossref","DOI":"10.1007\/b98874","volume-title":"Numerical Optimization","author":"J. Nocedal","year":"1999","unstructured":"Nocedal, J., Wright, S.J.: Numerical Optimization. Springer, New York (1999)"},{"key":"409_CR27","volume-title":"Nonlinear Programming","author":"D.P. Bertsekas","year":"1999","unstructured":"Bertsekas, D.P.: Nonlinear Programming, 2nd edn. Athena Scientific, Belmont (1999)","edition":"2"},{"key":"409_CR28","volume-title":"Introduction to the Theory of Neural Computation","author":"J. Hertz","year":"1991","unstructured":"Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Addison-Wesley, Redwood City (1991)"},{"key":"409_CR29","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/0893-6080(93)90003-F","volume":"6","author":"T. Denoeux","year":"1993","unstructured":"Denoeux, T., Lengell\u00e9, R.: Initializing back propagation networks with prototypes. Neural Netw. 6, 351\u2013363 (1993)","journal-title":"Neural Netw."},{"key":"409_CR30","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/BF02096261","volume":"46","author":"Z.-Q. Luo","year":"1993","unstructured":"Luo, Z.-Q., Tseng, P.: Error bounds and convergence analysis of feasible descent methods: a general approach. Ann. Oper. Res. 46, 157\u2013178 (1993)","journal-title":"Ann. Oper. Res."},{"key":"409_CR31","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-02431-3","volume-title":"Variational Analysis","author":"R.T. Rockafellar","year":"1998","unstructured":"Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis. Springer, New York (1998)"},{"key":"409_CR32","first-page":"1519","volume":"8","author":"K. Koh","year":"2007","unstructured":"Koh, K., Kim, S.-J., Boyd, S.: An interior-point method for large-scale \u2113 1-regularized logistic regression. J. Mach. Learn. Res. 8, 1519\u20131555 (2007)","journal-title":"J. Mach. Learn. Res."},{"key":"409_CR33","first-page":"33","volume-title":"Convex Optimization in Signal Processing and Communications","author":"A. Beck","year":"2010","unstructured":"Beck, A., Teboulle, M.: Gradient-Based Algorithms with Applications in Signal Recovery Problems. In: Palomar, D., Eldar, Y. (eds.) Convex Optimization in Signal Processing and Communications, pp. 33\u201388. Cambribge University Press, Cambribge (2010)"},{"key":"409_CR34","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, 221\u2013259 (2009)","journal-title":"Math. Program."},{"key":"409_CR35","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1137\/070704277","volume":"19","author":"A. Juditsky","year":"2009","unstructured":"Juditsky, A., Lan, G., Nemirovski, A., Shapiro, A.: Stochastic approximation approach to stochastic programming. SIAM J. Optim. 19, 1574\u20131609 (2009)","journal-title":"SIAM J. Optim."},{"key":"409_CR36","unstructured":"Tseng, P., Yun, S.: Incrementally updated gradient methods for constrained and regularized optimization. Report, Department of Mathematics Education, Sungkyunkwan University, Seoul (2012)"}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-013-0409-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10957-013-0409-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-013-0409-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T20:09:43Z","timestamp":1715976583000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10957-013-0409-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,11]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,3]]}},"alternative-id":["409"],"URL":"https:\/\/doi.org\/10.1007\/s10957-013-0409-2","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,11]]}}}