FFT-Based Fast Computation of Multivariate Kernel Density Estimators With Unconstrained Bandwidth Matrices

ABSTRACT The problem of fast computation of multivariate kernel density estimation (KDE) is still an open research problem. In our view, the existing solutions do not resolve this matter in a satisfactory way. One of the most elegant and efficient approach uses the fast Fourier transform. Unfortunately, the existing FFT-based solution suffers from a serious limitation, as it can accurately operate only with the constrained (i.e., diagonal) multivariate bandwidth matrices. In this article, we describe the problem and give a satisfactory solution. The proposed solution may be successfully used also in other research problems, for example, for the fast computation of the optimal bandwidth for KDE. Supplementary materials for this article are available online.

[1]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[2]  V. Raykar,et al.  Fast Computation of Kernel Estimators , 2010 .

[3]  Piotr Kulczycki,et al.  An algorithm for reducing the dimension and size of a sample for data exploration procedures , 2014, Int. J. Appl. Math. Comput. Sci..

[4]  Density estimation in R , 2014 .

[5]  A. Cuevas,et al.  A comparative study of several smoothing methods in density estimation , 1994 .

[6]  Joab R Winkler,et al.  Numerical recipes in C: The art of scientific computing, second edition , 1993 .

[7]  Ezequiel López-Rubio,et al.  Probability density function estimation with the frequency polygon transform , 2015, Inf. Sci..

[8]  David W. Scott,et al.  Frequency Polygons: Theory and Application , 1985 .

[9]  M. Rosenblatt,et al.  Multivariate k-nearest neighbor density estimates , 1979 .

[10]  B. Silverman,et al.  Kernel Density Estimation Using the Fast Fourier Transform , 1982 .

[11]  David W. Scott,et al.  Multivariate Density Estimation: Theory, Practice, and Visualization , 1992, Wiley Series in Probability and Statistics.

[12]  J. Simonoff.  Smoothing Methods in Statistics , 1998 .

[13]  C. Reinsch.  Smoothing by spline functions , 1967 .

[14]  Witold Andrzejewski,et al.  Graphics processing units in acceleration of bandwidth selection for kernel density estimation , 2013, Int. J. Appl. Math. Comput. Sci..

[15]  Malgorzata Charytanowicz,et al.  A complete gradient clustering algorithm formed with kernel estimators , 2010, Int. J. Appl. Math. Comput. Sci..

[16]  David W. Scott,et al.  Smoothing by weighted averaging of rounded points , 1990 .

[17]  D. W. Scott.  Averaged Shifted Histograms: Effective Nonparametric Density Estimators in Several Dimensions , 1985 .

[18]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[19]  M. Wand.  Fast Computation of Multivariate Kernel Estimators , 1994 .

[20]  Tarn Duong,et al.  Studying intracellular trafficking pathways with probabilistic density maps. , 2013, Methods in cell biology.

[21]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .