{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:12:54Z","timestamp":1764184374125,"version":"3.46.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Broadcom-VMware Industrial Chair, NSERC, and Mitacs","award":["ALLRP 577577-22"],"award-info":[{"award-number":["ALLRP 577577-22"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tetci.2024.3502463","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T14:20:39Z","timestamp":1733408439000},"page":"2894-2907","source":"Crossref","is-referenced-by-count":0,"title":["Convex-Concave Programming: An Effective Alternative for Optimizing Shallow Neural Networks"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5342-1824","authenticated-orcid":false,"given":"Mohammad","family":"Askarizadeh","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, École de Technologie Supérieure, University of Quebec, Montreal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8760-5218","authenticated-orcid":false,"given":"Alireza","family":"Morsali","sequence":"additional","affiliation":[{"name":"R&D, Aibrary, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5622-1783","authenticated-orcid":false,"given":"Sadegh","family":"Tofigh","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, École de Technologie Supérieure, University of Quebec, Montreal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9354-7544","authenticated-orcid":false,"given":"Kim Khoa","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, École de Technologie Supérieure, University of Quebec, Montreal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.2.246"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80131-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.875977"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1142\/S0219530516400042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/math7100992"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-56483-7_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01789-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623493258635"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008240227198"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"issue":"3","key":"ref12","first-page":"135","article-title":"Online algorithms and stochastic approximations","volume":"5","author":"Saad","year":"1998","journal-title":"Online Learn."},{"key":"ref13","first-page":"1","article-title":"The tradeoffs of large scale learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Bottou","year":"2007"},{"issue":"7","key":"ref14","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"ref15","first-page":"135","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"Hinton","year":"2012","journal-title":"Cited on"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref16"},{"article-title":"Geometry of optimization and implicit regularization in deep learning","year":"2017","author":"Neyshabur","key":"ref17"},{"key":"ref18","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu","year":"2019"},{"key":"ref19","first-page":"797","article-title":"Escaping from saddle pointsonline stochastic gradient for tensor decomposition","volume-title":"Proc. Conf. Learn. Theory","author":"Ge","year":"2015"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278854"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11634-008-0030-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143850"},{"key":"ref24","first-page":"470","article-title":"Stochastic difference of convex algorithm and its application to training deep Boltzmann machines","volume-title":"Proc. Artif. Intell. Statist.","author":"Nitanda","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2975051"},{"key":"ref26","first-page":"8895","article-title":"Piecewise linear regression via a difference of convex functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Siahkamari","year":"2020"},{"key":"ref27","first-page":"20176","article-title":"Faster algorithms for learning convex functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Siahkamari","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-0208(08)72402-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31484-6"},{"key":"ref30","first-page":"6942","article-title":"Stochastic optimization for DC functions and non-smooth non-convex regularizers with non-asymptotic convergence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2019"},{"key":"ref31","first-page":"4537","article-title":"Simple stochastic gradient methods for non-smooth non-convex regularized optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Metel","year":"2019"},{"key":"ref32","first-page":"10660","article-title":"Stochastic optimization for non-convex inf-projection problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yan","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/18M1231559"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-023-01344-2"},{"key":"ref35","first-page":"146","article-title":"Input convex neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amos","year":"2017"},{"key":"ref36","article-title":"Convex neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Bengio","year":"2006"},{"key":"ref37","first-page":"7695","article-title":"Neural networks are convex regularizers: Exact polynomial-time convex optimization formulations for two-layer networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pilanci","year":"2020"},{"key":"ref38","first-page":"1","article-title":"Convex regularization behind neural reconstruction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sahiner","year":"2021"},{"key":"ref39","first-page":"1","article-title":"Exact and relaxed convex formulations for shallow neural autoregressive models","volume-title":"Proc. Int. Conf. Acoust., Speech, Signal Process.","author":"Gupta","year":"2021"},{"key":"ref40","first-page":"1","article-title":"The concave-convex procedure (CCCP)","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"14","author":"Yuille","year":"2001"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-015-9294-x"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1144-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/21M1467134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2026004"},{"key":"ref45","first-page":"1","article-title":"Difference of convex functions programming for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Piot","year":"2014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05709-0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071358"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2016.1278445"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685637"},{"article-title":"Handbook of convergence theorems for (stochastic) gradient methods","year":"2023","author":"Garrigos","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-023-02199-z"},{"volume-title":"Real and Complex Analysis","year":"1987","author":"Rudin","key":"ref54"},{"key":"ref55","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist. JMLR Workshop Conf. Proc.","author":"Glorot","year":"2011"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"article-title":"Clarabel: An interior-point solver for conic programs with quadratic objectives","year":"2024","author":"Goulart","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492906370018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1137\/120886017"},{"issue":"1","key":"ref60","first-page":"2909","article-title":"CVXPY: A python-embedded modeling language for convex optimization","volume":"17","author":"Diamond","year":"2016","journal-title":"J. Mach. Learn. Res."},{"year":"2024","key":"ref61","article-title":"Kaggle: Your home for data science"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref63","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin","year":"2021"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/11095270\/10779190.pdf?arnumber=10779190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:06:02Z","timestamp":1764183962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10779190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":63,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3502463","relation":{},"ISSN":["2471-285X"],"issn-type":[{"type":"electronic","value":"2471-285X"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}