{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:04:54Z","timestamp":1758845094622,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,1,2]],"date-time":"2019-01-02T00:00:00Z","timestamp":1546387200000},"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":["Comput Optim Appl"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s10589-018-00057-7","type":"journal-article","created":{"date-parts":[[2019,1,2]],"date-time":"2019-01-02T06:52:33Z","timestamp":1546411953000},"page":"675-705","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A framework for parallel second order incremental optimization algorithms for solving partially separable problems"],"prefix":"10.1007","volume":"72","author":[{"given":"Kamer","family":"Kaya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Figen","family":"\u00d6ztoprak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7472-7032","authenticated-orcid":false,"given":"\u015e. \u0130lker","family":"Birbil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Taylan","family":"Cemgil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umut","family":"\u015eim\u015fekli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nurdan","family":"Kuru","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hazal","family":"Koptagel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Kaan","family":"\u00d6zt\u00fcrk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,2]]},"reference":[{"key":"57_CR1","unstructured":"Berahas, A.S., Nocedal, J., Tak\u00e1\u010d, M.: A multi-batch L-BFGS method for machine learning. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5\u201310, 2016, Barcelona, Spain, pp. 1055\u20131063 (2016)"},{"issue":"3","key":"57_CR2","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1137\/S1052623494268522","volume":"6","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas, D.P.: Incremental least squares methods and the extended Kalman filter. SIAM J. Optim. 6(3), 807\u2013822 (1996)","journal-title":"SIAM J. Optim."},{"key":"57_CR3","first-page":"2011","volume":"1\u201338","author":"DP Bertsekas","year":"2010","unstructured":"Bertsekas, D.P.: Incremental gradient, subgradient, and proximal methods for convex optimization: a survey. Optim. Mach. Learn. 1\u201338, 2011 (2010)","journal-title":"Optim. Mach. Learn."},{"issue":"1","key":"57_CR4","doi-asserted-by":"publisher","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(1), 29\u201351 (2007)","journal-title":"SIAM J. Optim."},{"issue":"4","key":"57_CR5","doi-asserted-by":"publisher","first-page":"2418","DOI":"10.1137\/080732158","volume":"32","author":"D Bozda\u011f","year":"2010","unstructured":"Bozda\u011f, D., \u00c7ataly\u00fcrek, \u00dc.V., Gebremedhin, A.H., Manne, F., Boman, E.G., \u00d6zg\u00fcner, F.: Distributed-memory parallel algorithms for distance-2 coloring and related problems in derivative computation. SIAM J. Sci. Comput. 32(4), 2418\u20132446 (2010)","journal-title":"SIAM J. Sci. Comput."},{"issue":"2","key":"57_CR6","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1137\/140954362","volume":"26","author":"RH Byrd","year":"2016","unstructured":"Byrd, R.H., Hansen, S.L., Nocedal, J., Singer, Y.: A stochastic quasi-Newton method for large-scale optimization. SIAM J. Optim. 26(2), 1008\u20131031 (2016)","journal-title":"SIAM J. Optim."},{"issue":"1\u20133","key":"57_CR7","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/BF01582063","volume":"63","author":"RH Byrd","year":"1994","unstructured":"Byrd, R.H., Nocedal, J., Schnabel, R.B.: Representations of quasi-Newton matrices and their use in limited memory methods. Math. Program. 63(1\u20133), 129\u2013156 (1994)","journal-title":"Math. Program."},{"key":"57_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/9780470747278","volume-title":"Nonnegative Matrix and Tensor Factorization","author":"A Cichocki","year":"2009","unstructured":"Cichocki, A., Zdunek, R., Phan, A.H., Amari, S.: Nonnegative Matrix and Tensor Factorization. Wiley, New York (2009)"},{"issue":"15","key":"57_CR9","doi-asserted-by":"publisher","first-page":"3914","DOI":"10.1109\/TSP.2015.2436357","volume":"63","author":"A Daneshmand","year":"2015","unstructured":"Daneshmand, A., Facchinei, F., Kungurtsev, V., Scutari, G.: Hybrid random\/deterministic parallel algorithms for convex and nonconvex big data optimization. IEEE Trans. Signal Process. 63(15), 3914\u20133929 (2015)","journal-title":"IEEE Trans. Signal Process."},{"issue":"7","key":"57_CR10","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TSP.2015.2399858","volume":"63","author":"F Facchinei","year":"2015","unstructured":"Facchinei, F., Scutari, G., Sagratella, S.: Parallel selective algorithms for nonconvex big data optimization. IEEE Trans. Signal Process. 63(7), 1874\u20131889 (2015)","journal-title":"IEEE Trans. Signal Process."},{"key":"57_CR11","doi-asserted-by":"crossref","unstructured":"Gebremedhin, A.H., Manne, F., Pothen, A.: Parallel distance-k coloring algorithms for numerical optimization. In: Euro-Par 2002 Parallel Processing\u20148th International Conference, pp. 912\u2013921 (2002)","DOI":"10.1007\/3-540-45706-2_130"},{"issue":"4","key":"57_CR12","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1137\/S0036144504444711","volume":"47","author":"AH Gebremedhin","year":"2005","unstructured":"Gebremedhin, A.H., Manne, F., Pothen, A.: What color is your Jacobian? Graph coloring for computing derivatives. SIAM Rev. 47(4), 629\u2013705 (2005)","journal-title":"SIAM Rev."},{"issue":"1","key":"57_CR13","doi-asserted-by":"publisher","first-page":"1:1","DOI":"10.1145\/2513109.2513110","volume":"40","author":"AH Gebremedhin","year":"2013","unstructured":"Gebremedhin, A.H., Nguyen, D., Patwary, MdMA, Pothen, A.: ColPack: software for graph coloring and related problems in scientific computing. ACM Trans. Math. Softw. 40(1), 1:1\u20131:31 (2013)","journal-title":"ACM Trans. Math. Softw."},{"key":"57_CR14","doi-asserted-by":"crossref","unstructured":"Gemulla, R., Nijkamp, E., Haas, P.J., Sismanis, Y.: Large-scale matrix factorization with distributed stochastic gradient descent. In: ACM SIGKDD (2011)","DOI":"10.1145\/2020408.2020426"},{"key":"57_CR15","unstructured":"Gower, R.M., Goldfarb, D., Richt\u00e1rik, P.: Stochastic block BFGS: squeezing more curvature out of data. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, New York, USA, 20\u201322 June 2016. PMLR, pp. 1869\u20131878"},{"issue":"1","key":"57_CR16","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10107-015-0897-y","volume":"151","author":"M G\u00fcrb\u00fczbalaban","year":"2015","unstructured":"G\u00fcrb\u00fczbalaban, M., Ozdaglar, A., Parrilo, P.: A globally convergent incremental Newton method. Math. Program. 151(1), 283\u2013313 (2015)","journal-title":"Math. Program."},{"issue":"4","key":"57_CR17","doi-asserted-by":"publisher","first-page":"19:1","DOI":"10.1145\/2827872","volume":"5","author":"FM Harper","year":"2015","unstructured":"Harper, F.M., Konstan, J.A.: The movielens datasets: history and context. ACM Trans. Interact. Intell. Syst. 5(4), 19:1\u201319:19 (2015)","journal-title":"ACM Trans. Interact. Intell. Syst."},{"issue":"2","key":"57_CR18","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/18.910572","volume":"47","author":"FR Kschischang","year":"2001","unstructured":"Kschischang, F.R., Frey, B.J., Loeliger, H.-A.: Factor graphs and the sum\u2013product algorithm. IEEE Trans. Inf. Theory 47(2), 498\u2013519 (2001)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"57_CR19","unstructured":"Lian, X., Huang, Y., Li, Y., Liu, J.: Asynchronous parallel stochastic gradient for nonconvex optimization. In: Advances in Neural Information Processing Systems, pp. 2737\u20132745 (2015)"},{"issue":"1","key":"57_CR20","first-page":"285","volume":"16","author":"J Liu","year":"2015","unstructured":"Liu, J., Wright, S.J., R\u00e9, C., Bittorf, V., Sridhar, S.: An asynchronous parallel stochastic coordinate descent algorithm. J. Mach. Learn. Res. 16(1), 285\u2013322 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"57_CR21","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1080\/10556789408805581","volume":"4","author":"OL Mangasarian","year":"1994","unstructured":"Mangasarian, O.L., Solodov, M.V.: Serial and parallel backpropation convergence via nonmonotone perturbed minimization. Optim. Methods Softw. 4, 103\u2013116 (1994)","journal-title":"Optim. Methods Softw."},{"key":"57_CR22","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-319-17689-5_11","volume-title":"Numerical Analysis and Optimization","author":"J Mare\u010dek","year":"2015","unstructured":"Mare\u010dek, J., Richt\u00e1rik, P., Tak\u00e1\u010d, M.: Distributed block coordinate descent for minimizing partially separable functions. In: Al-Baali, M., Grandinetti, L., Purnama, A. (eds.) Numerical Analysis and Optimization, pp. 261\u2013288. Springer, Berlin (2015)"},{"key":"57_CR23","first-page":"481","volume":"10","author":"DW Matula","year":"1968","unstructured":"Matula, D.W.: A min-max theorem for graphs with application to graph coloring. SIAM Rev. 10, 481\u2013482 (1968)","journal-title":"SIAM Rev."},{"key":"57_CR24","doi-asserted-by":"crossref","unstructured":"Mokhtari, A., Eisen, M., Ribeiro, A.: IQN: an incremental quasi-Newton method with local superlinear convergence rate. arXiv preprint \n                    arXiv:1702.00709\n                    \n                   (2017)","DOI":"10.1109\/ICASSP.2017.7952915"},{"key":"57_CR25","unstructured":"Moritz, P., Nishihara, R., Jordan, M.I.: A linearly-convergent stochastic L-BFGS algorithm. In: Artificial Intelligence and Statistics, pp. 249\u2013258 (2016)"},{"issue":"10","key":"57_CR26","doi-asserted-by":"publisher","first-page":"2718","DOI":"10.1109\/TSP.2013.2254478","volume":"61","author":"JFC Mota","year":"2013","unstructured":"Mota, J.F.C., Xavier, J.M.F., Aguiar, P.M.Q., P\u00fcschel, M.: D-ADMM: a communication-efficient distributed algorithm for separable optimization. IEEE Trans. Signal Process. 61(10), 2718\u20132723 (2013)","journal-title":"IEEE Trans. Signal Process."},{"key":"57_CR27","first-page":"2568","volume-title":"Advances in Neural Information Processing Systems","author":"X Pan","year":"2016","unstructured":"Pan, X., Lam, M., Tu, S., Papailiopoulos, D., Zhang, S., Jordan, M.I., Ramchandran, K., R\u00e9, C.: Cyclades: conflict-free asynchronous machine learning. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 2568\u20132576. Curran Associates Inc, Red Hook (2016)"},{"key":"57_CR28","first-page":"693","volume-title":"Advances in Neural Information Processing Systems","author":"B Recht","year":"2011","unstructured":"Recht, B., Re, C., Wright, S., Feng, N.: HOGWILD: a lock-free approach to parallelizing stochastic gradient descent. In: Shawe-Taylor, J., Zemel, R.S., Bartlett, P.L., Pereira, F., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 24, pp. 693\u2013701. Curran Associates Inc., Red Hook (2011)"},{"issue":"1\u20132","key":"57_CR29","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s10107-015-0901-6","volume":"156","author":"P Richt\u00e1rik","year":"2016","unstructured":"Richt\u00e1rik, P., Tak\u00e1\u010d, M.: Parallel coordinate descent methods for big data optimization. Math. Program. 156(1\u20132), 433\u2013484 (2016)","journal-title":"Math. Program."},{"key":"57_CR30","first-page":"2663","volume-title":"Advances in Neural Information Processing Systems","author":"NL Roux","year":"2012","unstructured":"Roux, N.L., Schmidt, M., Bach, F.R.: A stochastic gradient method with an exponential convergence\\_rate for finite training sets. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, pp. 2663\u20132671. Curran Associates Inc., Red Hook (2012)"},{"key":"57_CR31","unstructured":"Scherrer, C., Halappanavar, M., Tewari, A., Haglin, D.: Scaling up coordinate descent algorithms for large \n                    \n                      \n                    \n                    $$\\ell _1$$\n                    \n                      \n                        \n                          \u2113\n                          1\n                        \n                      \n                    \n                   regularization problems. In: Proceedings of the 29th International Conference on Machine Learning, ICML 2012, Edinburgh, Scotland, UK, June 26\u2013July 1 (2012)"},{"key":"57_CR32","unstructured":"Schraudolph, N.N., Yu, J., Gunter, S.: A stochastic quasi-Newton method for online convex optimization. In: Proceedings of the 11th International Conference Artificial Intelligence and Statistics (AISTATS), pp. 433\u2013440 (2007)"},{"key":"57_CR33","unstructured":"Shamir, O., Srebro, N., Zhang, T.: Communication efficient distributed optimization using an approximate Newton-type method. In: International Conference on Machine Learning (ICML) (2014)"},{"key":"57_CR34","doi-asserted-by":"crossref","unstructured":"Singh, A.P., Gordon, G.J.: A unified view of matrix factorization models. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Part II, number 5212, pp. 358\u2013373. Springer, Berlin (2008)","DOI":"10.1007\/978-3-540-87481-2_24"},{"key":"57_CR35","unstructured":"Sohl-Dickstein, J., Poole, B., Ganguli, S.: Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods. In: Proceedings of the 31th International Conference on Machine Learning (ICML), pp. 604\u2013612 (2014)"},{"issue":"1","key":"57_CR36","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1023\/A:1018366000512","volume":"11","author":"MV Solodov","year":"1998","unstructured":"Solodov, M.V.: Incremental gradient algorithms with stepsizes bounded away from zero. Comput. Optim. Appl. 11(1), 23\u201335 (1998)","journal-title":"Comput. Optim. Appl."},{"issue":"2","key":"57_CR37","doi-asserted-by":"publisher","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(2), 506\u2013531 (1998)","journal-title":"SIAM J. Optim."},{"issue":"2","key":"57_CR38","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1137\/15M1053141","volume":"27","author":"X Wang","year":"2017","unstructured":"Wang, X., Ma, S., Goldfarb, D., Liu, W.: Stochastic quasi-Newton methods for nonconvex stochastic optimization. SIAM J. Optim. 27(2), 927\u2013956 (2017)","journal-title":"SIAM J. Optim."},{"key":"57_CR39","doi-asserted-by":"crossref","unstructured":"Yousefian, F., Nedi\u0107, A., Shanbhag, U.V.: Stochastic quasi-Newton methods for non-strongly convex problems: convergence and rate analysis. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 4496\u20134503. IEEE (2016)","DOI":"10.1109\/CDC.2016.7798953"},{"key":"57_CR40","doi-asserted-by":"publisher","first-page":"103","DOI":"10.4086\/toc.2007.v003a006","volume":"3","author":"D Zuckerman","year":"2007","unstructured":"Zuckerman, D.: Linear degree extractors and the inapproximability of max clique and chromatic number. Theory Comput. 3, 103\u2013128 (2007)","journal-title":"Theory Comput."}],"container-title":["Computational Optimization and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-018-00057-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10589-018-00057-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-018-00057-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T19:43:54Z","timestamp":1577907834000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10589-018-00057-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,2]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["57"],"URL":"https:\/\/doi.org\/10.1007\/s10589-018-00057-7","relation":{},"ISSN":["0926-6003","1573-2894"],"issn-type":[{"type":"print","value":"0926-6003"},{"type":"electronic","value":"1573-2894"}],"subject":[],"published":{"date-parts":[[2019,1,2]]},"assertion":[{"value":"15 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2019","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}