Clustering by Compression Export

@article{Cilibrasi05, abstract = {We present a new method for clustering based on compression. The method does not use subject-specific features or background knowledge, and works as follows: First, we determine a parameter-free, universal, similarity distance, the normalized compression distance or NCD, computed from the lengths of compressed data files (singly and in pairwise concatenation). Second, we apply a hierarchical clustering method. The NCD is not restricted to a specific application area, and works across application area boundaries. A theoretical precursor, the normalized information distance, co-developed by one of the authors, is provably optimal. However, the optimality comes at the price of using the noncomputable notion of Kolmogorov complexity. We propose axioms to capture the real-world setting, and show that the NCD approximates optimality. To extract a hierarchy of clusters from the distance matrix, we determine a dendrogram (ternary tree) by a new quartet method and a fast heuristic to implement it. The method is implemented and available as public software, and is robust under choice of different compressors. To substantiate our claims of universality and robustness, we report evidence of successful application in areas as diverse as genomics, virology, languages, literature, music, handwritten digits, astronomy, and combinations of objects from completely different domains, using statistical, dictionary, and block sorting compressors. In genomics, we presented new evidence for major questions in Mammalian evolution, based on whole-mitochondrial genomic analysis: the Eutherian orders and the Marsupionta hypothesis against the Theria hypothesis.}, author = {Cilibrasi, R. and Vitanyi, P. M. B.}, citeulike-article-id = {752849}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TIT.2005.844059}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1412045}, doi = {10.1109/TIT.2005.844059}, journal = {Information Theory, IEEE Transactions on}, keywords = {algorithm, clustering, information-theory, technique}, number = {4}, pages = {1523--1545}, posted-at = {2007-09-17 18:26:08}, priority = {0}, title = {Clustering by Compression}, url = {http://dx.doi.org/10.1109/TIT.2005.844059}, volume = {51}, year = {2005} }

TY - JOUR ID - Cilibrasi05 L3 - citeulike-article-id:752849 N2 - We present a new method for clustering based on compression. The method does not use subject-specific features or background knowledge, and works as follows: First, we determine a parameter-free, universal, similarity distance, the normalized compression distance or NCD, computed from the lengths of compressed data files (singly and in pairwise concatenation). Second, we apply a hierarchical clustering method. The NCD is not restricted to a specific application area, and works across application area boundaries. A theoretical precursor, the normalized information distance, co-developed by one of the authors, is provably optimal. However, the optimality comes at the price of using the noncomputable notion of Kolmogorov complexity. We propose axioms to capture the real-world setting, and show that the NCD approximates optimality. To extract a hierarchy of clusters from the distance matrix, we determine a dendrogram (ternary tree) by a new quartet method and a fast heuristic to implement it. The method is implemented and available as public software, and is robust under choice of different compressors. To substantiate our claims of universality and robustness, we report evidence of successful application in areas as diverse as genomics, virology, languages, literature, music, handwritten digits, astronomy, and combinations of objects from completely different domains, using statistical, dictionary, and block sorting compressors. In genomics, we presented new evidence for major questions in Mammalian evolution, based on whole-mitochondrial genomic analysis: the Eutherian orders and the Marsupionta hypothesis against the Theria hypothesis. IS - 4 JF - Information Theory, IEEE Transactions on EP - 1545 TI - Clustering by Compression VL - 51 SP - 1523 KW - algorithm KW - clustering KW - information-theory KW - technique AU - Cilibrasi, R AU - Vitanyi, PMB PY - 2005/// UR - http://dx.doi.org/10.1109/TIT.2005.844059 ER -