{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:53:19Z","timestamp":1778345599193,"version":"3.51.4"},"reference-count":190,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007369","name":"Fondation Simone et Cino Del Duca, Institut de France, ANR","doi-asserted-by":"publisher","award":["MaSDOL-19-CE23-0017-01"],"award-info":[{"award-number":["MaSDOL-19-CE23-0017-01"]}],"id":[{"id":"10.13039\/100007369","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007369","name":"Fondation Simone et Cino Del Duca, Institut de France, ANR","doi-asserted-by":"publisher","award":["ANR-19-CHIA-SCAI-002"],"award-info":[{"award-number":["ANR-19-CHIA-SCAI-002"]}],"id":[{"id":"10.13039\/100007369","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HKRGC Project","award":["24203520"],"award-info":[{"award-number":["24203520"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tsp.2023.3301121","type":"journal-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:44:08Z","timestamp":1690998248000},"page":"3117-3148","source":"Crossref","is-referenced-by-count":11,"title":["Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1848-1724","authenticated-orcid":false,"given":"Aymeric","family":"Dieuleveut","sequence":"first","affiliation":[{"name":"Ecole Polytechnique, CMAP, UMR, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5400-1058","authenticated-orcid":false,"given":"Gersende","family":"Fort","sequence":"additional","affiliation":[{"name":"Institut de Mathématiques de Toulouse, Université de Toulouse, CNRS; UPS, Toulouse Cedex 9, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2058-0693","authenticated-orcid":false,"given":"Eric","family":"Moulines","sequence":"additional","affiliation":[{"name":"Ecole Polytechnique, CMAP, UMR, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4796-4483","authenticated-orcid":false,"given":"Hoi-To","family":"Wai","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0864-7"},{"key":"ref56","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"dekel","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref59","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume":"30","author":"alistarh","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref53","first-page":"2489","article-title":"Beyond the regret minimization barrier: Optimal algorithms for stochastic strongly-convex optimization","volume":"15","author":"hazan","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0008"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref168","article-title":"Stochastic approximation procedures with randomly varying truncations","author":"chen","year":"1986","journal-title":"Sci China Ser A"},{"key":"ref54","first-page":"1","article-title":"A survey of machine learning for big data processing","volume":"2016","author":"qiu","year":"2016","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012904439301"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1060.0213"},{"key":"ref177","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume":"26","author":"johnson","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref178","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","volume":"27","author":"defazio","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0007"},{"key":"ref175","volume":"178","author":"clarke","year":"2008","journal-title":"Nonsmooth Analysis and Control Theory"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3028013"},{"key":"ref173","article-title":"Analysis of nonsmooth stochastic approximation: The differential inclusion approach","author":"majewski","year":"0"},{"key":"ref174","volume":"264","author":"aubin","year":"2012","journal-title":"Differential Inclusions Set-Valued Maps and Viability Theory"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-012-0040-0"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-018-09409-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/19M1244925"},{"key":"ref45","first-page":"1","article-title":"Understanding the acceleration phenomenon via high-resolution differential equations","volume":"195","author":"shi","year":"2021","journal-title":"Math Program"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2182178"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0015"},{"key":"ref42","first-page":"2406","article-title":"Spiderboost and momentum: Faster variance reduction algorithms","author":"wang","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref41","first-page":"689","article-title":"SPIDER: Near-optimal non-convex optimization via stochastic path-integrated differential estimator","volume":"31","author":"fang","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref44","first-page":"5312","article-title":"A differential equation for modeling Nesterov's accelerated gradient method: Theory and insights","volume":"17","author":"su","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1137\/15M1053141"},{"key":"ref43","first-page":"29553","article-title":"Federated-EM with heterogeneity mitigation and variance reduction","volume":"34","author":"dieuleveut","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1006\/jcom.1994.1025"},{"key":"ref8","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0","journal-title":"Proc COMPSTAT"},{"key":"ref180","first-page":"2613","article-title":"SARAH: A novel method for machine learning problems using stochastic recursive gradient","volume":"70","author":"nguyen","year":"0","journal-title":"Proc ICML"},{"key":"ref7","first-page":"146","article-title":"Stochastic learning","author":"bottou","year":"2003","journal-title":"Machine Learning Summer School"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2878765"},{"key":"ref9","author":"pr\u00edncipe","year":"2011","journal-title":"Kernel Adaptive Filtering A Comprehensive Introduction"},{"key":"ref4","author":"ljung","year":"1983","journal-title":"Theory and Practice of Recursive Identification"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101561"},{"key":"ref6","author":"haykin","year":"2002","journal-title":"Adaptive Filter Theory"},{"key":"ref5","volume":"22","author":"benveniste","year":"2012","journal-title":"Adaptive Algorithms and Stochastic Approximations"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.2307\/2290005"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/SSP49050.2021.9513769"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1059655912"},{"key":"ref189","author":"neveu","year":"1975","journal-title":"Discrete-Parameter Martingales"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2744598"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414271"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/SSP49050.2021.9513846"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT50566.2022.9834827"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3203237"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056947"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3112139"},{"key":"ref35","author":"sayed","year":"2011","journal-title":"Adaptive Filters"},{"key":"ref34","volume":"48","author":"borkar","year":"2009","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/140962723"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/9781009051873"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2009.00698.x"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref149","article-title":"Efficient estimations from a slowly convergent Robbins-Monro process","author":"ruppert","year":"1988"},{"key":"ref33","article-title":"A stochastic path-integrated differential estimator expectation maximization algorithm","author":"fort","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97704-1"},{"key":"ref32","first-page":"7967","article-title":"Stochastic expectation maximization with variance reduction","volume":"31","author":"chen","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref147","first-page":"233","article-title":"A convergence theorem for non negative almost supermartingales and some applications","author":"robbins","year":"1971","journal-title":"Optimizing Methods in Statistics"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/16-AAP1272"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-023-10230-6"},{"key":"ref155","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","author":"shamir","year":"0","journal-title":"Proc ICML"},{"key":"ref156","first-page":"1","article-title":"Lower bounds for non-convex stochastic optimization","author":"arjevani","year":"2022","journal-title":"Math Program"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1137\/19M128908X"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1137\/19M128908X"},{"key":"ref151","first-page":"654","article-title":"‘Convex until proven guilty’: Dimension-free acceleration of gradient descent on non-convex functions","author":"carmon","year":"0","journal-title":"Proc ICML"},{"key":"ref152","article-title":"Non-convex finite-sum optimization via SCSG methods","volume":"30","author":"lei","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref150","first-page":"7","article-title":"Numerical optimization","volume":"35","author":"wright","year":"1999","journal-title":"Springer Sci"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2601299"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-5838-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-021-10023-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1018031103"},{"key":"ref20","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref159","article-title":"Problem complexity and method efficiency in optimization","author":"nemirovskij","year":"0"},{"key":"ref22","first-page":"1632","article-title":"Coordinate descent converges faster with the gauss-southwell rule than random selection","author":"nutini","year":"0","journal-title":"Proc ICML"},{"key":"ref157","article-title":"Non-asymptotic analysis of stochastic approximation algorithms for machine learning","author":"moulines","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92659-5_7"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref27","first-page":"1944","article-title":"Non-asymptotic analysis of biased stochastic approximation scheme","author":"karimi","year":"0","journal-title":"Conf Learn Theory"},{"key":"ref29","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1214\/16-AAP1272"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1287\/opre.43.6.1037"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0096509"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012993253534"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1137\/19M1281368"},{"key":"ref163","first-page":"20889","article-title":"Linearly converging error compensated SGD","volume":"33","author":"gorbunov","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref160","first-page":"5","article-title":"Stochastic convex optimization","volume":"2","author":"shalev-shwartz","year":"0","journal-title":"Proc COLT"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref13","volume":"35","author":"kushner","year":"2003","journal-title":"Stochastic Approximation and Recursive Algorithms and Applications"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39568-1"},{"key":"ref15","first-page":"2305","article-title":"Mirrorless mirror descent: A natural derivation of mirror descent","author":"gunasekar","year":"0","journal-title":"Proc AISTATS"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref14","article-title":"Tensor normal training for deep learning models","author":"ren","year":"2021"},{"key":"ref129","volume":"i","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176346060"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-69033-9"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1561\/2000000034"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1214\/17-STS611"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2329397"},{"key":"ref99","first-page":"73","article-title":"The SEM Algorithm: A Probabilistic Teacher Algorithm Derived from the EM Algorithm for the Mixture Problem","volume":"2","author":"celeux","year":"1985","journal-title":"Comput Stat Quart"},{"key":"ref124","first-page":"3056","article-title":"Supply curves in electricity markets: A framework for dynamic modeling and Monte Carlo forecasting","volume":"38","author":"y?ld?r?m","year":"2023","journal-title":"IEEE Trans Power Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1214\/lnms\/1215466757"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI52829.2022.9761641"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5.720250"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1049\/el:19940956"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/0470845899"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21236\/ADA307097"},{"key":"ref133","first-page":"5039","article-title":"Analysis of stochastic processes through replay buffers","author":"di-castro","year":"0","journal-title":"Proc ICML"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28982-8"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/BF00699098"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/78.324732"},{"key":"ref131","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc ICML"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-5564-6"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref130","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.860231"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1137\/1026034"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9467-7"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3128723"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683480"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2874687"},{"key":"ref88","author":"mclachlan","year":"2007","journal-title":"The EM Algorithm and Extensions"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012902417267"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.3150\/12-BEJ497"},{"key":"ref82","first-page":"5813","article-title":"Training quantized nets: A deeper understanding","volume":"30","author":"li","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref144","first-page":"6155","article-title":"Doublesqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","author":"tang","year":"0","journal-title":"Proc ICML"},{"key":"ref81","article-title":"High-accuracy low-precision training","author":"sa","year":"0"},{"key":"ref145","first-page":"1","article-title":"On perturbed proximal gradient algorithms","volume":"18","author":"atchad\u00e9","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00489"},{"key":"ref142","first-page":"129","article-title":"Natural compression for distributed deep learning","author":"horv\u00f3th","year":"0","journal-title":"Proc Math Sci Mach Learn"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00055"},{"key":"ref143","article-title":"Dimension-free bounds for low-precision training","volume":"32","author":"li","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref140","article-title":"Sparsified SGD with memory","volume":"31","author":"stich","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaab006"},{"key":"ref80","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"0","journal-title":"Proc ICML"},{"key":"ref79","article-title":"Training deep neural networks with low precision multiplications","author":"courbariaux","year":"0"},{"key":"ref108","article-title":"Towards frugal unsupervised detection of subtle abnormalities in medical imaging","author":"oudoumanessah","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput Assisted Intervention (MICCAI)"},{"key":"ref78","first-page":"2387","article-title":"Preserved central model for faster bidirectional compression in distributed settings","volume":"34","author":"philippenko","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1684(03)00106-3"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2012.6349725"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-019-09919-4"},{"key":"ref75","first-page":"2745","article-title":"Optimal algorithms for non-smooth distributed optimization in networks","volume":"31","author":"scaman","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref104","first-page":"2837","article-title":"On the global convergence of (fast) incremental expectation maximization methods","author":"karimi","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1137\/110831659"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/738"},{"key":"ref77","first-page":"1531","article-title":"Asynchronous stochastic convex optimization: The noise is in the noise and SGD don’t care","volume":"28","author":"chaturapruek","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_12"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426626"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1023\/A:1021987710829"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728659"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref190","author":"hall","year":"2014","journal-title":"Martingale Limit Theory and its Application"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2171686"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661429"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.863009"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.919629"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1137\/16M1057000"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2014.2357513"},{"key":"ref110","first-page":"1","article-title":"Blind source separation of noisy mixtures using a semi-parametric approach with application to heavy-tailed signals","author":"sahmoudi","year":"0","journal-title":"Proc 13th Eur Signal Process Conf (EUSIPCO)"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2932876"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2605676"},{"key":"ref67","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","author":"bernstein","year":"0","journal-title":"Proc ICML"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040409"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2005.843546"},{"key":"ref118","first-page":"2185","article-title":"Estimation of the weight parameter with SAEM for marked point processes applied to object detection","author":"boisbunon","year":"0","journal-title":"Proc 22nd Eur Signal Process Conf (EUSIPCO)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2743678"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638872"},{"key":"ref63","first-page":"2674","article-title":"Taming the wild: A unified analysis of hogwild-style algorithms","volume":"28","author":"sa","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38868-2_4"},{"key":"ref66","first-page":"1","article-title":"The error-feedback framework: Better rates for SGD with delayed gradients and compressed updates","volume":"21","author":"stich","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-008-9106-7"},{"key":"ref65","first-page":"3252","article-title":"Error feedback fixes signSGD and other gradient compression schemes","author":"karimireddy","year":"0","journal-title":"Proc ICML"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960359"},{"key":"ref60","volume":"159","author":"gersho","year":"2012","journal-title":"Vector Quantization and Signal Compression"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3033378"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414223"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-021-01665-8"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2899816"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1137\/19M1281368"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902599"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/10040758\/10202577.pdf?arnumber=10202577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:39:50Z","timestamp":1696880390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10202577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":190,"URL":"https:\/\/doi.org\/10.1109\/tsp.2023.3301121","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}