{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:52:40Z","timestamp":1770231160528,"version":"3.49.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2112606"],"award-info":[{"award-number":["OAC-2112606"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tpds.2025.3553066","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T17:43:38Z","timestamp":1742319818000},"page":"1253-1267","source":"Crossref","is-referenced-by-count":2,"title":["OmniLearn: A Framework for Distributed Deep Learning Over Heterogeneous Clusters"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8314-4745","authenticated-orcid":false,"given":"Sahil","family":"Tyagi","sequence":"first","affiliation":[{"name":"Department of Intelligent Systems Engineering School: Luddy School of Informatics, Computing and Engineering University: Indiana University Bloomington, Indiana, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1789-0145","authenticated-orcid":false,"given":"Prateek","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Intelligent Systems Engineering School: Luddy School of Informatics, Computing and Engineering University: Indiana University Bloomington, Indiana, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2005.847331"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref5","article-title":"On the utility of gradient compression in distributed training systems","author":"Agarwal","year":"2021"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref8","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Jiang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00008"},{"key":"ref10","article-title":"Gossip training for deep learning","author":"Blot","year":"2016"},{"key":"ref11","article-title":"Asynchronous decentralized parallel stochastic gradient descent","author":"Lian","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00097"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064220"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD60044.2023.00045"},{"key":"ref16","first-page":"693","article-title":"HOGWILD!: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Recht"},{"key":"ref17","article-title":"An empirical model of large-batch training","author":"McCandlish","year":"2018"},{"key":"ref18","article-title":"Large batch size training of neural networks with adversarial training and second-order information","author":"Yao","year":"2018"},{"key":"ref19","article-title":"Anytime minibatch: Exploiting stragglers in online distributed optimization","author":"Ferdinand","year":"2020"},{"key":"ref20","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016"},{"key":"ref21","article-title":"Train longer, generalize better: Closing the Generalization Gap in Large Batch Training of neural networks","author":"Hoffer","year":"2017"},{"key":"ref22","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00045"},{"key":"ref24","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref29","article-title":"Caltech-256 object category dataset","author":"Gregory","year":"2007"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref33","article-title":"Don\u2019t decay the learning rate, increase the batch size","author":"Smith","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386724"},{"key":"ref36","first-page":"685","article-title":"Deep learning with elastic averaging SGD","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020597"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040601"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452773"},{"key":"ref42","first-page":"45","article-title":"Taming unbalanced training workloads in deep learning with partial collective operations","volume-title":"Proc. 25th ACM SIGPLAN Symp. Princ. Pract. Parallel Program.","author":"Li"},{"key":"ref43","article-title":"Revisiting distributed synchronous SGD","author":"Chen","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378499"},{"key":"ref45","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref46","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"Zhang","year":"2017"},{"key":"ref47","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS49614.2020.00041"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/10969501\/10932719-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10969501\/10932719.pdf?arnumber=10932719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:42:16Z","timestamp":1745602936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10932719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":46,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3553066","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}