@inproceedings{efa6d149addb45599fd0c4d5a99795b4,
title = "EM∗: An em algorithm for big data",
abstract = "Existing data mining techniques, more particularly iterative learning algorithms, become overwhelmed with big data. While parallelism is an obvious and, usually, necessary strategy, we observe that both (1) continually revisiting data and (2) visiting all data are two of the most prominent problems especially for iterative, unsupervised algorithms like Expectation Maximization algorithm for clustering (EM-T). Our strategy is to embed EM-T into a non-linear hierarchical data structure(heap) that allows us to (1) separate data that needs to be revisited from data that does not and (2) narrow the iteration toward the data that is more difficult to cluster. We call this extended EM-T, EM∗. We show our EM∗ algorithm outperform EM-T algorithm over large real world and synthetic data sets. We lastly conclude with some theoretic underpinnings that explain why EM∗ is successful.",
keywords = "Big data, Clustering, Data mining, EM, Expectation maximization, Heap",
author = "Hasan Kurban and Mark Jenne and Dalkilic, {Mehmet M.}",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 3rd IEEE International Conference on Data Science and Advanced Analytics, DSAA 2016 ; Conference date: 17-10-2016 Through 19-10-2016",
year = "2016",
month = dec,
day = "22",
doi = "10.1109/DSAA.2016.40",
language = "English",
series = "Proceedings - 3rd IEEE International Conference on Data Science and Advanced Analytics, DSAA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "312--320",
booktitle = "Proceedings - 3rd IEEE International Conference on Data Science and Advanced Analytics, DSAA 2016",
address = "United States",
}