{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T09:06:56Z","timestamp":1774343216717,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1109\/tsp.2026.3671460","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:03:46Z","timestamp":1772831026000},"page":"1094-1108","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8883-7769","authenticated-orcid":false,"given":"Yihang","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Mathematics, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5008-4527","authenticated-orcid":false,"given":"Vincent Y. F.","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29931"},{"key":"ref3","first-page":"622","article-title":"ALoRA: Allocating low-rank adaptation for fine-tuning large language models","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies (Volume 1: Long Papers)","author":"Liu","year":"2024"},{"key":"ref4","first-page":"3274","article-title":"DyLoRA: Parameter-efficient tuning of pre-trained models using dynamic search-free low-rank adaptation","volume-title":"Proc. 17th Conf. Eur. Chapter Assoc. Comput. Linguistics.","author":"Valipour","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02437"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435939"},{"key":"ref10","article-title":"PIHLoRA: Physics-informed hypernetworks for low-ranked adaptation","volume-title":"Proc. AI Accelerated Mater. Des.-NeurIPS 2023 Workshop","author":"Majumdar","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/msd2.70030"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85747-8_4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2025.3588910"},{"key":"ref14","article-title":"LoRA-C: Parameter-efficient fine-tuning of robust CNN for IoT devices","author":"Ding","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489213"},{"key":"ref16","first-page":"41425","article-title":"SVFT: Parameter-efficient fine-tuning with singular vectors","volume":"37","author":"Lingam","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref17","article-title":"\u201cLoTR: Low tensor rank weight adaptation,\u201d","author":"Bershatsky","year":"2024"},{"key":"ref18","first-page":"3161","article-title":"LoRETTA: Low-rank economic tensor-train adaptation for ultra-low-parameter fine-tuning of large language models","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies (Volume 1: Long Papers)","author":"Yang","year":"2024"},{"key":"ref19","article-title":"PoLAR: Polar-decomposed low-rank adapter representation","author":"Lion","year":"2025"},{"key":"ref20","article-title":"The expressive power of low-rank adaptation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zeng","year":"2024"},{"key":"ref21","first-page":"21306","article-title":"LoRA training in the NTK regime has no spurious local minima","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Jang","year":"2024"},{"key":"ref22","first-page":"67758","article-title":"BLoB: Bayesian low-rank adaptation by backpropagation for large language models","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref23","first-page":"17783","article-title":"LoRA+: Efficient low rank adaptation of large models","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Hayou","year":"2024"},{"key":"ref24","article-title":"\u201cParameter-efficient fine-tuning for large models: A comprehensive survey,\u201d","volume-title":"Trans. Mach. Learn. Res.","author":"Han","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40663-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-51844-2"},{"key":"ref28","first-page":"30224","article-title":"LoRA training provably converges to a low-rank global minimum or it fails loudly (but it probably won\u2019t fail)","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Kim","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3233\/faia251185"},{"key":"ref30","article-title":"Bayesian low-rank adaptation for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Yang","year":"2024"},{"key":"ref31","article-title":"Adaptive budget allocation for parameter-efficient fine-tuning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhang","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139177801.004"},{"key":"ref33","volume-title":"Submodular Functions and Optimization","volume":"58","author":"Fujishige","year":"2005"},{"key":"ref34","first-page":"23610","article-title":"A kernel-based view of language model fine-tuning","volume-title":"Int. Conf. Mach. Learn.","author":"Malladi","year":"2023"},{"key":"ref35","article-title":"LoRA vs full fine-tuning: An illusion of equivalence","author":"Shuttleworth","year":"2024"},{"key":"ref36","first-page":"498","article-title":"Guarantees for greedy maximization of non-submodular functions with applications","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Bian","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/9781601987570"},{"key":"ref38","first-page":"797","article-title":"Escaping from saddle points\u2014online stochastic gradient for tensor decomposition","volume-title":"Proc. Conf. Learn. Theory","author":"Ge","year":"2015"},{"key":"ref39","article-title":"Matrix completion has no spurious local minimum","volume":"29","author":"Ge","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0006528"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC60832.2023.00072"},{"key":"ref44","first-page":"25471","article-title":"Achieving high accuracy with PINNs via energy natural gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn","author":"M\u00fcller","year":"2023"},{"key":"ref45","first-page":"4005","article-title":"Near-optimal sketchy natural gradients for physics-informed neural networks","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Mckay","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1324"},{"key":"ref47","first-page":"26809","article-title":"PLATON: Pruning large transformer models with upper confidence bound of weight importance","volume-title":"Int. Conf. Mach. Learn.","author":"Zhang","year":"2022"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/11345506\/11422995.pdf?arnumber=11422995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T05:33:26Z","timestamp":1774330406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11422995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tsp.2026.3671460","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}