{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:09:25Z","timestamp":1730200165927,"version":"3.28.0"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"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":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9672001","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"1092-1101","source":"Crossref","is-referenced-by-count":1,"title":["Is Systematic Data Sharding able to Stabilize Asynchronous Parameter Server Training?"],"prefix":"10.1109","author":[{"given":"Nikodimos","family":"Provatas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Konstantinou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nectarios","family":"Koziris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219837"},{"key":"ref38","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"International Conference on Machine Learning"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref32"},{"key":"ref31","article-title":"Rmsprop and equilibrated adaptive learning rates for nonconvex optimization","author":"bengio","year":"2015","journal-title":"corr abs\/1502 04390"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920931"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref35","first-page":"2","article-title":"Parameter server for distributed machine learning","volume":"6","author":"li","year":"2013","journal-title":"NIPS Big Learning Workshop"},{"key":"ref34","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3299887.3299891"},{"key":"ref61","first-page":"4387","article-title":"The non-iid data quagmire of decentralized machine learning","author":"hsieh","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref28","article-title":"Exploiting data distribution in distributed learning of deep classification models under the parameter server architecture","volume":"2971","author":"provatas","year":"2021","journal-title":"Proceedings of the VLDB 2021 PhD Workshop (VLDB-PhD 2021)"},{"key":"ref27","first-page":"2350","article-title":"Staleness-aware async-sgd for distributed deep learning","author":"zhang","year":"2016","journal-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-0940-7"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref2"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"shallue","year":"2019","journal-title":"Journal of Machine Learning Research"},{"year":"0","key":"ref22","article-title":"Distributed communication package - torch.distributed — PyTorch 1.6.0 documentation"},{"year":"0","key":"ref21","article-title":"Measuring the Limits of Data Parallel Training for Neural Networks"},{"year":"0","key":"ref24"},{"year":"0","key":"ref23","article-title":"MultiWorkerMirroredStrategy"},{"key":"ref26","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006412"},{"year":"0","key":"ref50","article-title":"Dimensionality reduction - rdd-based api"},{"year":"0","key":"ref51","article-title":"Clustering"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588565"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487696"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384468"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23808-6_10"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421296"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177734"},{"key":"ref53","first-page":"803","article-title":"Slow and stale gradients can win the race: Error-runtime trade-offs in distributed sgd","author":"dutta","year":"2018","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref52","first-page":"1145","article-title":"Asynchronous byzantine machine learning (the case of sgd)","author":"damaskinos","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","first-page":"2266","article-title":"Modeling order in neural word embeddings at scale","volume":"37","author":"trask","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning"},{"key":"ref40","first-page":"171","article-title":"Model accuracy and runtime tradeoff in distributed deep learning: A systematic study","author":"gupta","year":"0","journal-title":"2016 IEEE 16th International Conference on Data Mining (ICDM) ICDM"},{"key":"ref12","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"key":"ref13","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362707"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"ref16","first-page":"1235","article-title":"Mllib: Machine learning in apache spark","volume":"17","author":"meng","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Horovod: fast and easy distributed deep learning in tensorflow","year":"2018","author":"sergeev","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343211.3343218"},{"key":"ref19","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: end-to-end speech recognition in english and mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-5209-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378421"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"year":"0","key":"ref46","article-title":"sklearn.cluster.kmeans¶"},{"year":"0","key":"ref45","article-title":"sklearn.decomposition.incrementalpca¶"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref48"},{"year":"0","key":"ref47","article-title":"Hadoop"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"year":"0","key":"ref41"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"On lines and planes of closest fit to systems of points in space","volume":"2","author":"f r s","year":"1901","journal-title":"The London Edinburgh and Dublin Philosophical Magazine and Journal of Science"},{"key":"ref43","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2021,12,15]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09672001.pdf?arnumber=9672001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:26Z","timestamp":1652201726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9672001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9672001","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}