{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T06:13:52Z","timestamp":1769235232273,"version":"3.49.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:00:00Z","timestamp":1559260800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:00:00Z","timestamp":1559260800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF\u20131409261"],"award-info":[{"award-number":["CCF\u20131409261"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER grant CCF\u20131149225"],"award-info":[{"award-number":["CAREER grant CCF\u20131149225"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["ONR\/SPAWAR contract N660011824020"],"award-info":[{"award-number":["ONR\/SPAWAR contract N660011824020"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"crossref","award":["No. 31\/1031"],"award-info":[{"award-number":["No. 31\/1031"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Taub Foundation","award":["Taub Foundation"],"award-info":[{"award-number":["Taub Foundation"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Math Imaging Vis"],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1007\/s10851-019-00889-w","type":"journal-article","created":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T17:02:47Z","timestamp":1559322167000},"page":"279-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["The Global Optimization Geometry of Shallow Linear Neural Networks"],"prefix":"10.1007","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3856-0375","authenticated-orcid":false,"given":"Zhihui","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Soudry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4358-5304","authenticated-orcid":false,"given":"Yonina C.","family":"Eldar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael B.","family":"Wakin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,31]]},"reference":[{"key":"889_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, N., Allen-Zhu, Z., Bullins, B., Hazan, E., Ma, T.: Finding approximate local minima faster than gradient descent. In: Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing, pp. 1195\u20131199. ACM (2017)","DOI":"10.1145\/3055399.3055464"},{"issue":"1","key":"889_CR2","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0893-6080(89)90014-2","volume":"2","author":"P Baldi","year":"1989","unstructured":"Baldi, P., Hornik, K.: Neural networks and principal component analysis: learning from examples without local minima. Neural Netw. 2(1), 53\u201358 (1989)","journal-title":"Neural Netw."},{"key":"889_CR3","unstructured":"Bhojanapalli, S., Neyshabur, B., Srebro, N.: Global optimality of local search for low rank matrix recovery. In: Advances in Neural Information Processing Systems, pp. 3873\u20133881 (2016)"},{"key":"889_CR4","unstructured":"Blum, A., Rivest, R.L.: Training a 3-node neural network is NP-complete. In: Advances in Neural Information Processing Systems (NIPS), pp. 494\u2013501 (1989)"},{"issue":"16","key":"889_CR5","doi-asserted-by":"publisher","first-page":"4293","DOI":"10.1109\/TSP.2017.2708040","volume":"65","author":"M Borgerding","year":"2017","unstructured":"Borgerding, M., Schniter, P., Rangan, S.: Amp-inspired deep networks for sparse linear inverse problems. IEEE Trans. Signal Process. 65(16), 4293\u20134308 (2017)","journal-title":"IEEE Trans. Signal Process."},{"issue":"1","key":"889_CR6","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/PL00011391","volume":"89","author":"RH Byrd","year":"2000","unstructured":"Byrd, R.H., Gilbert, J.C., Nocedal, J.: A trust region method based on interior point techniques for nonlinear programming. Math. Program. 89(1), 149\u2013185 (2000)","journal-title":"Math. Program."},{"key":"889_CR7","unstructured":"Carmon, Y., Duchi, J.C., Hinder, O., Sidford, A.: Accelerated methods for non-convex optimization. arXiv preprint \narXiv:1611.00756\n\n (2016)"},{"key":"889_CR8","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719857","volume-title":"Trust Region Methods","author":"AR Conn","year":"2000","unstructured":"Conn, A.R., Gould, N.I., Toint, P.L.: Trust Region Methods. SIAM, Philadelphia (2000)"},{"key":"889_CR9","unstructured":"Curtis, F.E., Robinson, D.P.: Exploiting negative curvature in deterministic and stochastic optimization. arXiv preprint \narXiv:1703.00412\n\n (2017)"},{"issue":"4","key":"889_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303\u2013314 (1989)","journal-title":"Math. Control Signals Syst."},{"key":"889_CR11","unstructured":"Du, S.S., Lee, J.D., Tian, Y.: When is a convolutional filter easy to learn? arXiv preprint \narXiv:1709.06129\n\n (2017)"},{"key":"889_CR12","unstructured":"Ge, R., Huang, F., Jin, C., Yuan, Y.: Escaping from saddle points\u2014online stochastic gradient for tensor decomposition. In: Conference on Learning Theory, pp. 797\u2013842 (2015)"},{"key":"889_CR13","unstructured":"Ge, R., Jin, C., Zheng, Y.: No spurious local minima in nonconvex low rank problems: a unified geometric analysis. In: International Conference on Machine Learning, pp. 1233\u20131242 (2017)"},{"key":"889_CR14","unstructured":"Ge, R., Lee, J.D., Ma, T.: Matrix completion has no spurious local minimum. In: Advances in Neural Information Processing Systems, pp. 2973\u20132981 (2016)"},{"key":"889_CR15","doi-asserted-by":"crossref","unstructured":"Haeffele, B.D., Vidal, R.: Global optimality in neural network training. In: Conference on Computer Vision and Pattern Recognition, pp. 7331\u20137339 (2017)","DOI":"10.1109\/CVPR.2017.467"},{"key":"889_CR16","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411","volume-title":"Matrix Analysis","author":"RA Horn","year":"2012","unstructured":"Horn, R.A., Johnson, C.R.: Matrix Analysis. Cambridge University Press, Cambridge (2012)"},{"issue":"5","key":"889_CR17","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359\u2013366 (1989)","journal-title":"Neural Netw."},{"key":"889_CR18","unstructured":"Jin, C., Ge, R., Netrapalli, P., Kakade, S.M., Jordan, M.I.: How to escape saddle points efficiently. In: International Conference on Machine Learning, pp. 1724\u20131732 (2017)"},{"issue":"5","key":"889_CR19","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1109\/LSP.2016.2548245","volume":"23","author":"US Kamilov","year":"2016","unstructured":"Kamilov, U.S., Mansour, H.: Learning optimal nonlinearities for iterative thresholding algorithms. IEEE Signal Process. Lett. 23(5), 747\u2013751 (2016)","journal-title":"IEEE Signal Process. Lett."},{"key":"889_CR20","unstructured":"Kawaguchi, K.: Deep learning without poor local minima. In: Advances in Neural Information Processing Systems, pp. 586\u2013594 (2016)"},{"key":"889_CR21","unstructured":"Laurent, T., von Brecht, J.: Deep linear neural networks with arbitrary loss: all local minima are global. arXiv preprint \narXiv:1712.01473\n\n (2017)"},{"issue":"7553","key":"889_CR22","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)","journal-title":"Nature"},{"key":"889_CR23","unstructured":"Lee, J.D., Panageas, I., Piliouras, G., Simchowitz, M., Jordan, M.I., Recht, B.: First-order methods almost always avoid saddle points. arXiv preprint \narXiv:1710.07406\n\n (2017)"},{"key":"889_CR24","unstructured":"Lee, J.D., Simchowitz, M., Jordan, M.I., Recht, B.: Gradient descent only converges to minimizers. In: Conference on Learning Theory, pp. 1246\u20131257 (2016)"},{"key":"889_CR25","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1093\/imaiai\/iay003","volume":"8","author":"Q Li","year":"2019","unstructured":"Li, Q., Zhu, Z., Tang, G.: The non-convex geometry of low-rank matrix optimization. Inf. Inference: J. IMA 8, 51\u201396 (2019)","journal-title":"Inf. Inference: J. IMA"},{"key":"889_CR26","unstructured":"Li, X., Wang, Z., Lu, J., Arora, R., Haupt, J., Liu, H., Zhao, T.: Symmetry, saddle points, and global geometry of nonconvex matrix factorization. arXiv preprint \narXiv:1612.09296\n\n (2016)"},{"key":"889_CR27","unstructured":"Li, X., Zhu, Z., So, A.M.C., Vidal, R.: Nonconvex robust low-rank matrix recovery. arXiv preprint \narXiv:1809.09237\n\n (2018)"},{"key":"889_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2018.2829166","volume":"99","author":"Y Li","year":"2018","unstructured":"Li, Y., Zhang, Y., Huang, X., Ma, J.: Learning source-invariant deep hashing convolutional neural networks for cross-source remote sensing image retrieval. IEEE Trans. Geosci. Remote Sens. 99, 1\u201316 (2018)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"889_CR29","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.isprsjprs.2018.09.014","volume":"146","author":"Y Li","year":"2018","unstructured":"Li, Y., Zhang, Y., Huang, X., Yuille, A.L.: Deep networks under scene-level supervision for multi-class geospatial object detection from remote sensing images. ISPRS J. Photogramm. Remote Sens. 146, 182\u2013196 (2018)","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"issue":"4","key":"889_CR30","doi-asserted-by":"publisher","first-page":"2426","DOI":"10.1137\/16M110109X","volume":"27","author":"H Liu","year":"2017","unstructured":"Liu, H., Yue, M.C., Man-Cho So, A.: On the estimation performance and convergence rate of the generalized power method for phase synchronization. SIAM J. Optim. 27(4), 2426\u20132446 (2017)","journal-title":"SIAM J. Optim."},{"key":"889_CR31","unstructured":"Lu, H., Kawaguchi, K.: Depth creates no bad local minima. arXiv preprint \narXiv:1702.08580\n\n (2017)"},{"key":"889_CR32","doi-asserted-by":"crossref","unstructured":"Mousavi, A., Patel, A.B., Baraniuk, R.G.: A deep learning approach to structured signal recovery. In: 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 1336\u20131343 (2015)","DOI":"10.1109\/ALLERTON.2015.7447163"},{"issue":"1","key":"889_CR33","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s10107-006-0706-8","volume":"108","author":"Y Nesterov","year":"2006","unstructured":"Nesterov, Y., Polyak, B.T.: Cubic regularization of newton method and its global performance. Math. Program. 108(1), 177\u2013205 (2006)","journal-title":"Math. Program."},{"key":"889_CR34","unstructured":"Nouiehed, M., Razaviyayn, M.: Learning deep models: critical points and local openness. arXiv preprint \narXiv:1803.02968\n\n (2018)"},{"key":"889_CR35","unstructured":"Park, D., Kyrillidis, A., Carmanis, C., Sanghavi, S.: Non-square matrix sensing without spurious local minima via the burer-monteiro approach. In: Artificial Intelligence and Statistics, pp. 65\u201374 (2017)"},{"key":"889_CR36","unstructured":"Qu, Q., Zhang, Y., Eldar, Y.C., Wright, J.: Convolutional phase retrieval via gradient descent. arXiv preprint \narXiv:1712.00716\n\n (2017)"},{"key":"889_CR37","unstructured":"Safran, I., Shamir, O.: Spurious local minima are common in two-layer relu neural networks. arXiv preprint \narXiv:1712.08968\n\n (2017)"},{"key":"889_CR38","volume-title":"Artificial Neural Networks","author":"RJ Schalkoff","year":"1997","unstructured":"Schalkoff, R.J.: Artificial Neural Networks, vol. 1. McGraw-Hill, New York (1997)"},{"key":"889_CR39","unstructured":"Soudry, D., Carmon, Y.: No bad local minima: Data independent training error guarantees for multilayer neural networks. arXiv preprint \narXiv:1605.08361\n\n (2016)"},{"key":"889_CR40","unstructured":"Soudry, D., Hoffer, E.: Exponentially vanishing sub-optimal local minima in multilayer neural networks. arXiv preprint \narXiv:1702.05777\n\n (2017)"},{"key":"889_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10208-017-9365-9","volume":"18","author":"J Sun","year":"2018","unstructured":"Sun, J., Qu, Q., Wright, J.: A geometric analysis of phase retrieval. Found. Comput. Math. 18, 1\u201368 (2018)","journal-title":"Found. Comput. Math."},{"issue":"2","key":"889_CR42","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1109\/TIT.2016.2632162","volume":"63","author":"J Sun","year":"2017","unstructured":"Sun, J., Qu, Q., Wright, J.: Complete dictionary recovery over the sphere I: overview and the geometric picture. IEEE Trans. Inf. Theory 63(2), 853\u2013884 (2017)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"889_CR43","unstructured":"Tian, Y.: An analytical formula of population gradient for two-layered relu network and its applications in convergence and critical point analysis. In: International Conference on Machine Learning, pp. 3404\u20133413 (2017)"},{"key":"889_CR44","unstructured":"Werbos, P.: Beyond regression: new fools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard University (1974)"},{"key":"889_CR45","unstructured":"Yun, C., Sra, S., Jadbabaie, A.: Global optimality conditions for deep neural networks. arXiv preprint \narXiv:1707.02444\n\n (2017)"},{"key":"889_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Li, Q., Tang, G., Wakin, M.B.: The global optimization geometry of low-rank matrix optimization. arXiv preprint \narXiv:1703.01256\n\n (2017)","DOI":"10.1109\/GlobalSIP.2017.8309166"},{"issue":"13","key":"889_CR47","doi-asserted-by":"publisher","first-page":"3614","DOI":"10.1109\/TSP.2018.2835403","volume":"66","author":"Z Zhu","year":"2018","unstructured":"Zhu, Z., Li, Q., Tang, G., Wakin, M.B.: Global optimality in low-rank matrix optimization. IEEE Trans. Signal Process. 66(13), 3614\u20133628 (2018)","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Journal of Mathematical Imaging and Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-019-00889-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10851-019-00889-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-019-00889-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,29]],"date-time":"2020-05-29T23:06:42Z","timestamp":1590793602000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10851-019-00889-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,31]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["889"],"URL":"https:\/\/doi.org\/10.1007\/s10851-019-00889-w","relation":{},"ISSN":["0924-9907","1573-7683"],"issn-type":[{"value":"0924-9907","type":"print"},{"value":"1573-7683","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,31]]},"assertion":[{"value":"3 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}