Abstract
We propose to use the Zipfian distribution as a kernel for the design of a nonparametric classifier in contrast to the Gaussian distribution used in most kernel methods. We show that the Zipfian distribution takes into account multifractal nature of data and gives a true picture of scaling properties inherent in data. We also show that this new look at data structure can lead to a simple classifier that can, for some tasks, outperform more complex systems.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
ARYA, S., MOUNT, D.M., NARAYAN, O. (1996), “Accounting for Boundary Effects in Nearest Neighbor Searching”, Discrete and Computational Geometry, 16, 155–176.
BACHE, K., and LICHMAN, M. (2013), “UCI Machine Learning Repository”, University of California, School of Information and Computer Science, Irvine CA, http://archive.ics.uci.edu/ml
BORS, A.G., and NASIOS, N. (2013), “Kernel Bandwidth Estimation for Nonparametric Data Segmentation”, go to: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.7219.
CAMASTRA, F. (2003), “Data Dimensionality Estimation Methods: A Survey”, Pattern Recognition, 36, 2945–2954.
CAMASTRA, P., and VINCIARELLI, A. (2001), “Intrinstic Dimension Estimation of Data: An Approach Based on Grassberger-Procaccia’s Algorithm”, Neural Processing Letters, 14(1), 27–34.
COVER, T.M., and HART, P.E. (1967), “Nearest Neighbor Pattern Classification”, IEEE Transactions in Information Theory, IT-13(1), 23–27.
GRASSBERGER, P., and PROCACCIA, I. (1983), “Measuring the Strangeness of Strange Attractors”, Physica, 9D, 189–208.
HAKL, F., JIŘINA, M., and RICHTER-WAS, E. (2005), “Hadronic Tau’s Identification Using Artificial Neural Network”, ATLAS Physics Communication, ATL-COMPHYS-2005-044, CERN, Geneve, http://www.marceljirina.cz/files/hadronic-tau-sidentification-using-artificial-neural-network.pdf
HERBRICH, R. (2002), Learning Kernel Classifiers. Theory and Algorithms, Cambridge MA; London UK: The MIT Press.
HERBRICH, R. (2001), Learning Kernel Classifiers. Theory and Algorithms, Cambridge MA: The MIT Press.
JIŘINA, M., and JIŘINA, JR., M. (2008), “Apparatus for Assessing a Control Value”, patent pending under number PV 2008-245; Z 7576, submitted on 22 April 2008 to the Industrial Property Office, Prague, Czech Republic.
JIŘINA, M., and JIŘINA JR., M. (2008), “Correlation Integral Decomposition for Classification. in Artificial Neural Networks”, Lecture Notes in Computer Science Vol. 5164, Berlin: Springer, pp 62–71.
JIŘINA, M., and JIŘINA JR., M. (2009), “Classification by the Use of Decomposition of Correlation Integral” in Studies in Computational Intelligence Vol 205, Foundations of Computational Intelligence Vol 5, Berlin: Springer, pp. 39–55
JIŘINA, M., and JIŘINA JR., M. (2013), “Utilization of Singularity Exponent in Nearest Neighbor Based Classifier”, Journal of Classification, 30(1), 3–29.
LUCAS, S.M. (2008), “Algoval: Algorithm Evaluation over the Web”, http://algoval.essex.ac.uk.
MANDELBROT, B.B. (1982), The Fractal Theory of Nature, New York: W. H. Freeman and Co.
MASLOV, V.P. (2005), “On a General Theorem of Set Theory Leading to the Gibbs, Bose-Einstein, and Pareto Distributions as Well as to the Zipf-Mandelbrot Law for the Stock Market”, Mathematical Notes, 78(6), 807–813.
PAREDES, R. (2008), “CPW: Class and Prototype Weights Learning”, http://www.dsic.upv.es/~rparedes/research/CPW/index.html.
PAREDES, R., and VIDAL, E. (2006), “Learning Weighted Metrics to Minimize Nearest Neighbor Classification Error”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(7), 1100–1110.
SCHMULAND, B (2003), “Random Harmonic Series”, American Mathematical Monthly 110, 407–416.
SCHÖLKOPF, B., and SMOLA, A.J. (2002), Learning with Kernels. Support Vector Machines, Regularization, Optimization, and Beyond, Cambridge MA; London UK: The MIT Press.
SCOTT, D.W. (1992), Multivariate Density Estimation. Theory, Practice, and Visualization, New York: John Wiley and Sons.
SILVERMAN, B.W. (1992), Density Estimation for Statistics and Data Analysis, CRC Monographs on Statistics and Applied Probability, London: Chapman and Hall.
ZIPF, G.K. (1968), The Psycho-Biology of Language. An Introduction to Dynamic Philology, Cambridge: The MIT Press.
ZUO, W., WANG, K., ZHANG, H., and ZHANG, D. (2007), “Kernel Difference-Weighted k-Nearest Neighbors Classification”, Lecture Notes in Computer Science Vol. 4682, Berlin; Heidelberg: Springer-Verlag, pp. 861–870.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by Technology Agency CR under project of series ALFA No. TA01010490 and by the Czech Technical University in Prague, Faculty of Information Technology, RVO: 68407700. We also thank the Institute of Computer Science of the Czech Academy of Sciences for its support in submitting application of patent for the classifier described.
Rights and permissions
About this article
Cite this article
Jiřina, M., Jiřina, M. Classification Using the Zipfian Kernel. J Classif 32, 305–326 (2015). https://doi.org/10.1007/s00357-015-9174-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00357-015-9174-2