{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:52Z","timestamp":1780949212397,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"crossref","award":["ANR-23-CE23-0024"],"award-info":[{"award-number":["ANR-23-CE23-0024"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"crossref","award":["ANR-23-CE94-0001"],"award-info":[{"award-number":["ANR-23-CE94-0001"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["2316420"],"award-info":[{"award-number":["2316420"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/msp.2025.3646570","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:38:42Z","timestamp":1776109122000},"page":"107-121","source":"Crossref","is-referenced-by-count":0,"title":["Low-Rank Tensor Decompositions for the Theory of Neural Networks: Understanding deep learning through the lens of tensor formats [Special Issue on the Mathematics of Deep Learning]"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6036-2124","authenticated-orcid":false,"given":"Ricardo","family":"Borsoi","sequence":"first","affiliation":[{"name":"Research Center for Automatic Control, French National Center for Scientific Research (CNRS), Université de Lorraine, Nancy, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1154-5909","authenticated-orcid":false,"given":"Konstantin","family":"Usevich","sequence":"additional","affiliation":[{"name":"Research Center for Automatic Control, French National Center for Scientific Research (CNRS), Université de Lorraine, Nancy, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marianne","family":"Clausel","sequence":"additional","affiliation":[{"name":"Research Center for Automatic Control, French National Center for Scientific Research (CNRS), Université de Lorraine, Nancy, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2017.2690524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2014.2298533"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/07070111x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28027-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2021.3074329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21236\/ada604494"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/2200000059"},{"key":"ref8","first-page":"442","article-title":"Tensorizing neural networks","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst.  Vol. 1 (NIPS)","author":"Novikov","year":"2015"},{"key":"ref9","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Hu","year":"2022"},{"key":"ref10","first-page":"698","article-title":"On the expressive power of deep learning: A tensor analysis","volume-title":"Proc. Conf. Learn. Theory","author":"Cohen","year":"2016"},{"key":"ref11","first-page":"32,595","article-title":"A tensor decomposition perspective on second-order RNNs","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Lizaire","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-023-09620-w"},{"key":"ref13","first-page":"10,310","article-title":"On the expressive power of deep polynomial neural networks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst","author":"Kileel","year":"2019"},{"key":"ref14","first-page":"1","article-title":"Identifiability of deep polynomial neural networks","volume-title":"Proc. 39th Int. Conf. Neural Inf. Process. Syst.","author":"Usevich","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/18m119834x"},{"key":"ref16","article-title":"Beating the perils of non-convexity: Guaranteed training of neural networks using tensor methods","author":"Janzamin","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaaa036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/140991546"},{"key":"ref19","first-page":"1","article-title":"Learning two-layer neural networks with symmetric inputs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ge","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3564246.3585209"},{"key":"ref21","first-page":"1498","article-title":"Expressive power of tensor-network factorizations for probabilistic modeling","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Glasser","year":"2019"},{"key":"ref22","first-page":"7301","article-title":"Tesseract: Tensorised actors for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Mahajan","year":"2021"},{"key":"ref23","first-page":"205","article-title":"Algorithms for learning a mixture of linear classifiers","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Chen","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s40574-025-00472-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/16m1108388"},{"key":"ref26","article-title":"Expressive power of recurrent neural networks","author":"Khrulkov","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/20m1381046"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21861"},{"key":"ref29","first-page":"1051","article-title":"On the connection between learning two-layer neural networks and tensor decomposition","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Mondelli","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2022.3164837"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/mcas.2023.3267921"},{"key":"ref32","article-title":"Geometry-aware training of factorized layers in tensor Tucker format","author":"Zangrando","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.174"},{"key":"ref34","first-page":"504","article-title":"Understanding generalization in deep learning via tensor methods","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Li","year":"2020"},{"key":"ref35","first-page":"3032","article-title":"Transformed low-rank parameterization can help robust generalization for tensor neural networks","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Wang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2015509117"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icdm.2010.127"},{"key":"ref38","article-title":"Deep learning and quantum entanglement: Fundamental connections with implications to network design","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Levine","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-021-09543-4"},{"key":"ref40","first-page":"955","article-title":"Convolutional rectifier networks as generalized tensor decompositions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen","year":"2016"},{"key":"ref41","first-page":"13,485","article-title":"Efficient algorithms for learning depth-2 neural networks with general ReLU activations","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Awasthi","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaaa042"},{"key":"ref43","article-title":"Learning one-hidden-layer neural networks with landscape design","author":"Ge","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CAMSAP58249.2023.10403509"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-021-09550-5"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/79\/11479943\/11480035.pdf?arnumber=11480035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:32Z","timestamp":1780948472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11480035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":45,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/msp.2025.3646570","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}