{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T01:05:01Z","timestamp":1782176701890,"version":"3.54.5"},"reference-count":120,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3509860","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:06:16Z","timestamp":1733339176000},"page":"1501-1513","source":"Crossref","is-referenced-by-count":8,"title":["Deep Loss Convexification for Learning Iterative Models"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0921-8298","authenticated-orcid":false,"given":"Ziming","family":"Zhang","sequence":"first","affiliation":[{"name":"Electrical & Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Shao","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Data Science, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1749-3599","authenticated-orcid":false,"given":"Fangzhou","family":"Lin","sequence":"additional","affiliation":[{"name":"Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1314-8456","authenticated-orcid":false,"given":"Haichong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5375-9254","authenticated-orcid":false,"given":"Elke","family":"Rundensteiner","sequence":"additional","affiliation":[{"name":"Data Science, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A comprehensive survey on point cloud registration","author":"Huang","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767965"},{"key":"ref3","first-page":"8812","article-title":"PRNet: Self-supervised learning for partial-to-partial registration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref4","volume-title":"Fixed Point Theorems","volume":"66","author":"Smart","year":"1980"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950779"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00832-0_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2044061"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/2200000058"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2184319.2184343"},{"key":"ref10","first-page":"2698","article-title":"An alternative view: When does SGD escape local minima?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kleinberg"},{"key":"ref11","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref12","article-title":"SGD converges to global minimum in deep learning via star-convex path","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref13","first-page":"1894","article-title":"Near-optimal methods for minimizing star-convex functions and beyond","volume-title":"Proc. Conf. Learn. Theory","author":"Hinder"},{"key":"ref14","article-title":"Towards understanding the role of over-parametrization in generalization of neural networks","author":"Neyshabur","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0706-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2016.71"},{"key":"ref17","first-page":"1894","article-title":"Near-optimal methods for minimizing star-convex functions and beyond","volume-title":"Proc. 33rd Conf. Learn. Theory","author":"Hinder"},{"key":"ref18","first-page":"1315","article-title":"SGD for structured nonconvex functions: Learning rates, minibatching and interpolation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Gower"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92711-0_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01267"},{"key":"ref21","article-title":"Adversarial weight perturbation helps robust generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref22","article-title":"LossPlot: A better way to visualize loss landscapes","author":"Bain","year":"2021"},{"key":"ref23","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019"},{"key":"ref24","first-page":"1802","article-title":"Exploring the landscape of spatial robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engstrom"},{"key":"ref25","article-title":"The loss landscape of overparameterized neural networks","author":"Cooper","year":"2018"},{"key":"ref26","first-page":"9722","article-title":"Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Simsek"},{"key":"ref27","first-page":"14 848","article-title":"Embedding principle of loss landscape of deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3004124"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/9.887636"},{"key":"ref30","article-title":"Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima","author":"Loh","year":"2013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2789291"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965893"},{"key":"ref33","article-title":"Adaptively solving the local-minimum problem for deep neural networks","author":"Wang","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798816"},{"key":"ref35","first-page":"9815","article-title":"Adaptive methods for nonconvex optimization","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Reddi"},{"key":"ref36","article-title":"Regularized deep learning with nonconvex penalties","author":"Vettam","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref43","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref45","first-page":"12 979","article-title":"Contrastive learning inverts the data generating process","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zimmermann"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00830"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00724"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00312"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01257"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01086"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00656"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2015.03.022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3DIM.2007.39"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S1077-3142(03)00009-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.003"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3033695"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00733"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00362"},{"key":"ref60","article-title":"PCRNet: Point cloud registration network using PointNet encoding","author":"Sarode","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01184"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00259"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00425"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2020.05.002"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2656380"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00685"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2924684"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.111"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2809549"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00767"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_38"},{"key":"ref72","article-title":"Deep image homography estimation","author":"DeTone","year":"2016"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.402"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01569"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00192"},{"key":"ref76","article-title":"A survey of planar homography estimation techniques","author":"Agarwal","year":"2005"},{"key":"ref77","article-title":"Deep learning of diffeomorphisms for optimal reparametrizations of shapes","author":"Celledoni","year":"2022"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00246"},{"key":"ref79","first-page":"121","article-title":"An iterative image registration technique with an application to stereo vision","volume-title":"Proc. Imag. Understanding Workshop","author":"Lucas"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref81","first-page":"597","article-title":"Convergence analysis of two-layer neural networks with ReLU activation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00992"},{"key":"ref83","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"ref84","article-title":"FlexConv: Continuous kernel convolutions with differentiable kernel sizes","author":"Romero","year":"2021"},{"key":"ref85","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref86","article-title":"Long expressive memory for sequence modeling","author":"Rusch","year":"2021"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00572"},{"key":"ref88","article-title":"Coupled oscillatory recurrent neural network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","author":"Konstantin Rusch","year":"2020"},{"key":"ref89","article-title":"Lipschitz recurrent neural networks","author":"Erichson","year":"2020"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3064878"},{"key":"ref91","article-title":"CKConv: Continuous kernel convolution for sequential data","author":"Romero","year":"2021"},{"key":"ref92","article-title":"Recurrent batch normalization","author":"Cooijmans","year":"2016"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045509"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref95","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref97","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00905"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00639"},{"key":"ref101","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2513405"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_47"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00733"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_43"},{"key":"ref107","doi-asserted-by":"crossref","DOI":"10.1109\/VCIP49819.2020.9301874","article-title":"Unsupervised point cloud registration via salient points analysis (SPA)","author":"Kadam","year":"2020"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341249"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00034"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970946"},{"key":"ref111","article-title":"Coherent point drift networks: Unsupervised learning of non-rigid point set registration","author":"Wang","year":"2019"},{"key":"ref112","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-16902-1_14","article-title":"Learning generalized non-rigid multimodal biomedical image registration from generic point set data","author":"Baum","year":"2022"},{"key":"ref113","article-title":"RAR: Region-aware point cloud registration","author":"Hao","year":"2021"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00548"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8508-7_38"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3268273"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01044"},{"key":"ref119","first-page":"6237","article-title":"LF-Net: Learning local features from images","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ono"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01462"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10873290\/10777605-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10777605.pdf?arnumber=10777605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T05:35:33Z","timestamp":1738992933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":120,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3509860","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}