{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T15:22:53Z","timestamp":1774797773077,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/bigdata.2017.8257942","type":"proceedings-article","created":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T22:47:28Z","timestamp":1516056448000},"page":"331-338","source":"Crossref","is-referenced-by-count":9,"title":["Understanding and optimizing the performance of distributed machine learning applications on apache spark"],"prefix":"10.1109","author":[{"given":"Celestine","family":"Dunner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Parnell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kubilay","family":"Atasu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manolis","family":"Sifalakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haralampos","family":"Pozidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Introducing the webb spam corpus: Using email spam to identify web spam automatically","author":"webb","year":"2006","journal-title":"Proceedings of the Third Conference on Email and Anti-Spam (CEAS)"},{"key":"ref11","article-title":"Improving pyspark performance: Spark performance beyond the jvm","author":"karau","year":"2016","journal-title":"PyData Amsterdam"},{"key":"ref12","article-title":"TensorFrames on Google's TensorFlow and Apache Spark","author":"hunter","year":"2016","journal-title":"Bay Area Spark Meetup"},{"key":"ref13","author":"samuel","year":"2016","journal-title":"IBMSparkGPU"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.procs.2015.07.286","article-title":"Big data analytics in the cloud: Spark on hadoop vs mpi\/openmp on beowulf","author":"reyes-ortiz","year":"2015","journal-title":"Procedia Computer Science ser NSDI’ 12 Elsevier"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840606"},{"key":"ref16","first-page":"293","article-title":"Making sense of performance in data analytics frameworks","author":"ousterhout","year":"2015","journal-title":"USENIX Symposium on Networked Systems Design and Implementation (NSDI)"},{"key":"ref17","article-title":"Tupleware:” big” data, big analytics, small clusters","author":"crotty","year":"2015","journal-title":"CIDR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806945"},{"key":"ref4","author":"smith","year":"2016","journal-title":"Cocoa A general framework for communication-efficient distributed optimization"},{"key":"ref3","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"0","journal-title":"Advances in Neural Information Processing Systems 2011"},{"key":"ref6","article-title":"MPI: A message-passing interface standard","author":"forum","year":"1994","journal-title":"Univ Tennessee"},{"key":"ref5","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation"},{"key":"ref8","author":"hall","year":"2009","journal-title":"Breeze A Numerical Processing Library for Scala"},{"key":"ref7","author":"smith","year":"2015","journal-title":"PRoxCoCoA+"},{"key":"ref2","article-title":"Multiverso","year":"2015","journal-title":"Microsoft"},{"key":"ref1","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"Proc USENIX Conf Operating System Design and Implementations"},{"key":"ref9","author":"walt","year":"0","journal-title":"The NumPy Array A structure for efficient numerical computation„"}],"event":{"name":"2017 IEEE International Conference on Big Data (Big Data)","location":"Boston, MA","start":{"date-parts":[[2017,12,11]]},"end":{"date-parts":[[2017,12,14]]}},"container-title":["2017 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8241556\/8257893\/08257942.pdf?arnumber=8257942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T11:04:35Z","timestamp":1570619075000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8257942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2017.8257942","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}