{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:31:55Z","timestamp":1784309515217,"version":"3.55.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["ERC Advanced grant 694888, C-SENSE"],"award-info":[{"award-number":["ERC Advanced grant 694888, C-SENSE"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Imaging"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tci.2020.3032101","type":"journal-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T19:46:26Z","timestamp":1603309586000},"page":"1471-1485","source":"Crossref","is-referenced-by-count":25,"title":["The Practicality of Stochastic Optimization in Imaging Inverse Problems"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4996-6079","authenticated-orcid":false,"given":"Junqi","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Egiazarian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Golbabaee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2327-236X","authenticated-orcid":false,"given":"Mike","family":"Davies","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/42.363108"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.834793"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1137\/16M108104X"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1118\/1.2789499"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/83.660997"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2012.12.022"},{"key":"ref39","first-page":"315?323","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9099-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2709265"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1137\/16M1064064"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-013-9150-3"},{"key":"ref33","first-page":"1?122","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"boyd","year":"2011","journal-title":"Found Trends Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2307\/1993056"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.20.000439"},{"key":"ref30","first-page":"4400","article-title":"Accelerating sense-type MR image reconstruction algorithms with incremental gradients","author":"muckley","year":"0","journal-title":"Proc Intl Soc Mag Res Med"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-013-0465-7"},{"key":"ref36","first-page":"2618?2626","article-title":"A quasi-newton proximal splitting method","author":"becker","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0892-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/140971233"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0502-7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2258354"},{"key":"ref61","author":"kodak-lossless-true-color-image-suite","year":"0"},{"key":"ref63","article-title":"Unlocbox: A matlab convex optimization toolbox for proximal-splitting methods","author":"perraudin","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/42.241889"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-019-09617-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/44\/11\/311"},{"key":"ref65","first-page":"242?255","article-title":"Mini-batch semi-stochastic gradient descent in the proximal setting","volume":"10","author":"kone?n?","year":"2016","journal-title":"IEEE J Sel Top Signal Process"},{"key":"ref66","article-title":"Gradient methods for minimizing composite objective function","author":"nesterov","year":"2007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2350962"},{"key":"ref67","first-page":"657?669","article-title":"Total variation projection with first order schemes","volume":"20","author":"fadili","year":"2010","journal-title":"IEEE Trans Image Process"},{"key":"ref68","first-page":"3639?3647","article-title":"Tight complexity bounds for optimizing composite objectives","author":"woodworth","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-016-1018-7"},{"key":"ref2","first-page":"177?186","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0","journal-title":"Proc COMPSTAT"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1173-0"},{"key":"ref22","first-page":"5975?5984","article-title":"A simple stochastic variance reduced algorithm with fast convergence rates","author":"zhou","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","first-page":"8194?8244","article-title":"Katyusha: The first direct acceleration of stochastic gradient methods","volume":"18","author":"allen-zhu","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab3d07"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/17M1134834"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-017-0231-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/2\/1\/015008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2013.6737048"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2763583"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2047910"},{"key":"ref58","volume":"87","author":"nesterov","year":"2013","journal-title":"Introductory Lectures on Convex Optimization A Basic Course"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1117\/12.766355"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999820"},{"key":"ref54","first-page":"52?67","article-title":"Regularization by denoising: Clarifications and new interpretations","volume":"5","author":"reehorst","year":"2018","journal-title":"I IEEE Transactions on Computers"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1137\/16M1102884"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2019.2893568"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-015-0746-4"},{"key":"ref11","article-title":"Improving FISTA: Faster, smarter and greedier","author":"liang","year":"2018","journal-title":"arXiv 1811 01430"},{"key":"ref40","first-page":"5200?5209","article-title":"SGD: General analysis and improved rates","volume":"97","author":"gower","year":"0","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-010-0251-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0957-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/19M1271798"},{"key":"ref15","first-page":"1?30","article-title":"Minimizing finite sums with the stochastic average gradient","author":"schmidt","year":"2013","journal-title":"Math Program"},{"key":"ref82","first-page":"9896?9905","article-title":"On Markov chain gradient descent","author":"sun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"1646?1654","article-title":"Saga: A fast incremental gradient method with support for non-strongly convex composite objectives","author":"defazio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2011.09.039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/140961791"},{"key":"ref18","first-page":"567?599","article-title":"Stochastic dual coordinate ascent methods for regularized loss minimization","volume":"14","author":"shalev-shwartz","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"372?376","article-title":"A method of solving a convex programming problem with convergence rate o (1\/k2)","volume":"27","author":"nesterov","year":"0","journal-title":"Sov Math Doklady"},{"key":"ref80","first-page":"427?438","article-title":"Rest-katyusha: Exploiting the solution's structure via scheduled restart schemes","author":"tang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 31"},{"key":"ref4","first-page":"15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0420-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/0716071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S096249291600009X"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9569-8_10"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2007.4379013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2028250"},{"key":"ref46","first-page":"1?9","article-title":"Stochastic optimization with importance sampling for regularized loss minimization","author":"zhao","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","first-page":"3352?3361","article-title":"Fixing mini-batch sequences with hierarchical robust partitioning","author":"wang","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref48","first-page":"962?982","article-title":"Importance sampling for minibatches","volume":"19","author":"csiba","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref47","first-page":"1110?1119","article-title":"Even faster accelerated coordinate descent using non-uniform sampling","author":"allen-zhu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref41","article-title":"Optimization for deep learning: Theory and algorithms","author":"sun","year":"0","journal-title":"arXiv 1912 08957"},{"key":"ref44","first-page":"2233?2241","article-title":"Mixed robust\/average submodular partitioning: Fast algorithms, guarantees, and applications","author":"wei","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/44\/11\/311"}],"container-title":["IEEE Transactions on Computational Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6745852\/8977810\/09234749.pdf?arnumber=9234749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:21Z","timestamp":1651080741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9234749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tci.2020.3032101","relation":{},"ISSN":["2333-9403","2334-0118","2573-0436"],"issn-type":[{"value":"2333-9403","type":"electronic"},{"value":"2334-0118","type":"electronic"},{"value":"2573-0436","type":"print"}],"subject":[],"published":{"date-parts":[[2020]]}}}