Corpus ID: 6971397

Demystifying Information-Theoretic Clustering

@article{Steeg2014DemystifyingIC,
  title={Demystifying Information-Theoretic Clustering},
  author={Greg Ver Steeg and Aram Galstyan and Fei Sha and Simon DeDeo},
  journal={ArXiv},
  year={2014},
  volume={abs/1310.4210}
}
  • Greg Ver Steeg, Aram Galstyan, +1 author Simon DeDeo
  • Published 2014
  • Mathematics, Computer Science, Physics
  • ArXiv
  • 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… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 23 CITATIONS

    The Information Sieve

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Entropy-based Graph Clustering - A Simulated Annealing Approach

    Evaluation algorithm for clustering quality based on information entropy

    Distributed information-theoretic biclustering

    VIEW 1 EXCERPT
    CITES METHODS

    Maximally Informative Hierarchical Representations of High-Dimensional Data

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Information State: A Representation for Dynamic Processes Using Information Theory

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Unsupervised Nearest Neighbors Clustering With Application to Hyperspectral Images

    FILTER CITATIONS BY YEAR

    2014
    2019

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES

    Information-based clustering.

    VIEW 2 EXCERPTS

    Nonparametric Information Theoretic Clustering Algorithm

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Information theoretic clustering of sparse cooccurrence data

    Information Theoretic Clustering

    VIEW 1 EXCERPT

    Objective Criteria for the Evaluation of Clustering Methods

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL