Search Machine Learning Repository: @inproceedings{icml2014c1_steeg14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {Demystifying Information-Theoretic Clustering},
    Url = {http://jmlr.org/proceedings/papers/v32/steeg14.pdf},
    Abstract = {We propose a novel method for clustering data which is grounded in information-theoretic principles and requires no parametric assumptions. Previous attempts to use information theory to define clusters in an assumption-free way are based on maximizing mutual information between data and cluster labels. We demonstrate that this intuition suffers from a fundamental conceptual flaw that causes clustering performance to deteriorate as the amount of data increases. Instead, we return to the axiomatic foundations of information theory to define a meaningful clustering measure based on the notion of consistency under coarse-graining for finite data.},
    Author = {Greg V. Steeg and Aram Galstyan and Fei Sha and Simon Dedeo},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {19-27}
   }