{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:32:56Z","timestamp":1758126776349,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2015-04011"],"award-info":[{"award-number":["2015-04011"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tsp.2024.3361714","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:51:11Z","timestamp":1707159071000},"page":"1015-1031","source":"Crossref","is-referenced-by-count":1,"title":["Distributed Continual Learning With CoCoA in High-Dimensional Linear Regression"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7366-5981","authenticated-orcid":false,"given":"Martin","family":"Hellkvist","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Uppsala University, Uppsala, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8978-2990","authenticated-orcid":false,"given":"Ay\u00e7a","family":"\u00d6z\u00e7elikkale","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Uppsala University, Uppsala, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-5468","authenticated-orcid":false,"given":"Anders","family":"Ahl\u00e9n","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Uppsala University, Uppsala, Sweden"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3143372"},{"key":"ref5","first-page":"4028","article-title":"How catastrophic can catastrophic forgetting be in linear regression?","volume-title":"Proc. 35th Conf. Learn. Theory","author":"Evron","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref7","first-page":"1072","article-title":"A theoretical analysis of catastrophic forgetting through the NTK overlap matrix","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","author":"Doan","year":"2021"},{"article-title":"Generalisation guarantees for continual learning with orthogonal gradient descent","year":"2020","author":"Bennani","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9780470374122"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2436363"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2102756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2811757"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3226113"},{"article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","year":"2015","author":"Goodfellow","key":"ref14"},{"article-title":"Toward understanding catastrophic forgetting in continual learning","year":"2019","author":"Nguyen","key":"ref15"},{"article-title":"Towards robust evaluations of continual learning","year":"2019","author":"Farquhar","key":"ref16"},{"key":"ref17","article-title":"Anatomy of catastrophic forgetting: Hidden representations and task semantics","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ramasesh","year":"2021"},{"key":"ref18","first-page":"21078","article-title":"Theory on forgetting and generalization of continual learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn., in Machine Learning Research","volume":"202","author":"Lin","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900461"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3009007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/984622.984626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.2007111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2990086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/2200000051"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2385045"},{"issue":"1","key":"ref27","first-page":"8590","article-title":"CoCoA: A general framework for communication-efficient distributed optimization","volume":"18","author":"Smith","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"3068","article-title":"Communication-efficient distributed dual coordinate ascent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaggi","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2016.1278445"},{"key":"ref30","first-page":"4536","article-title":"Cola: Decentralized linear learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104412"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.927480"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3078625"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2333560"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2966273"},{"key":"ref36","first-page":"12073","article-title":"Federated continual learning with weighted inter-client transfer","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Yoon","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00534"},{"article-title":"Continual learning with distributed optimization: Does CoCoA forget?","year":"2022","author":"Hellkvist","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3106441"},{"article-title":"Three scenarios for continual learning","year":"2019","author":"van de Ven","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref43","first-page":"6147","article-title":"Distributed optimization for overparameterized problems: Achieving optimal dimension independent communication complexity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2022"},{"key":"ref44","article-title":"Decentralized learning for overparameterized problems: A multi-agent kernel approximation approach","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Khanduri","year":"2022"},{"article-title":"Distributed optimization for over-parameterized learning","year":"2019","author":"Zhang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992924"},{"key":"ref47","first-page":"6840","article-title":"Local SGD optimizes overparameterized neural networks in polynomial time","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Deng","year":"2022"},{"key":"ref48","article-title":"Optimal regularization can mitigate double descent","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nakkiran","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1214\/21-aos2133"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2984716"},{"key":"ref51","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Stich","year":"2019"},{"issue":"189","key":"ref52","first-page":"1","article-title":"One-shot federated learning: Theoretical limits and algorithms to achieve them","volume":"22","author":"Salehkaleybar","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","article-title":"Order optimal one-shot distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sharifnassab","year":"2019"},{"article-title":"LOCO: Distributing ridge regression with random projections","year":"2015","author":"Heinze","key":"ref54"},{"key":"ref55","first-page":"875","article-title":"DUAL-LOCO: Distributing statistical estimation using random projections","volume-title":"Proc. 19th Int. Conf. Artif. Intell. Statist.","volume":"51","author":"Heinze","year":"2016"},{"key":"ref56","article-title":"Efficient large-scale distributed training of conditional maximum entropy models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Mann","year":"2009"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cdc.2012.6426691"},{"key":"ref58","first-page":"24313","article-title":"Communication-efficient SGD: From local SGD to one-shot averaging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Spiridonoff","year":"2021"},{"volume-title":"Adaptive Filter Theory","year":"1996","author":"Haykin","key":"ref59"},{"article-title":"MNIST handwritten digit database","year":"2010","author":"LeCun","key":"ref60"},{"key":"ref61","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Zenke","year":"2017"},{"key":"ref62","first-page":"1177","article-title":"Random features for large-scale kernel machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rahimi","year":"2008"},{"volume-title":"Pattern Recognition and Machine Learning","year":"2006","author":"Bishop","key":"ref63"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3237174"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1214\/11-EJS602"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/10347386\/10422966.pdf?arnumber=10422966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T04:36:18Z","timestamp":1710390978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tsp.2024.3361714","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2024]]}}}