{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:21:53Z","timestamp":1755220913561,"version":"3.43.0"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3587330","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T17:40:43Z","timestamp":1752687643000},"page":"2803-2818","source":"Crossref","is-referenced-by-count":0,"title":["A Large Dimensional Analysis of Multi-Task Semi-Supervised Learning"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1910-4210","authenticated-orcid":false,"given":"Victor","family":"L\u00e9ger","sequence":"first","affiliation":[{"name":"Laboratoire d’Informatique de Grenoble, Université Grenoble Alpes, Saint Martin d’Hères, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-2090","authenticated-orcid":false,"given":"Romain","family":"Couillet","sequence":"additional","affiliation":[{"name":"Laboratoire d’Informatique de Grenoble, Université Grenoble Alpes, Saint Martin d’Hères, France"}]}],"member":"263","reference":[{"article-title":"The computational limits of deep learning","year":"2022","author":"Thompson","key":"ref1"},{"volume-title":"Tools for Conviviality","year":"1973","author":"Illich","key":"ref2"},{"issue":"94","key":"ref3","first-page":"1","article-title":"Consistent semi-supervised graph regularization for high dimensional data","volume":"22","author":"Mai","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","first-page":"321","article-title":"Learning with local and global consistency","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Zhou","year":"2003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972825.83"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/6173.003.0007","article-title":"Risks of semi-supervised learning: How unlabeled data can degrade performance of generative classifiers","volume-title":"Semi-Supervised Learning","author":"Cozman","year":"2006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"ref8","article-title":"Does unlabeled data provably help? Worst-case analysis of the sample complexity of semi-supervised learning","volume-title":"Proc. Annu. Conf. Comput. Learn. Theory","author":"Ben-David","year":"2008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053557"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014067"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1090\/surv\/089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/08-AAP548"},{"key":"ref13","article-title":"Random matrix theory proves that deep learning representations of GAN-data behave as Gaussian mixtures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Seddik","year":"2020"},{"key":"ref14","article-title":"Transductive learning via spectral graph partitioning","volume-title":"Proc. 20th Int. Conf. Mach. Learn. (ICML-2003)","author":"Joachims","year":"2003"},{"key":"ref15","article-title":"Semi-supervised learning using gaussian fields and harmonic functions","volume-title":"Proc. 20th Int. Conf. Mach. Learn. (ICML-2003)","author":"Zhu","year":"2003"},{"issue":"1","key":"ref16","first-page":"3074","article-title":"A random matrix analysis and improvement of semi-supervised learning for large dimensional data","volume":"19","author":"Mai","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2274735"},{"key":"ref19","article-title":"Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture","volume-title":"Proc. 26th Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"206","author":"Nguyen","year":"2023"},{"key":"ref20","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","journal-title":"3rd Int. Conf. Learn. Represent. (ICLR)"},{"key":"ref21","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2019","journal-title":"Int. Conf. Learn. Represent."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2030463"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/9781009128490"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11082111.pdf?arnumber=11082111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T04:37:19Z","timestamp":1754627839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11082111\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3587330","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2025]]}}}