Quarterly of Applied Mathematics

Quarterly of Applied Mathematics

Online ISSN 1552-4485; Print ISSN 0033-569X



Kernel density estimation via diffusion and the complex exponentials approximation problem

Author: Piero Barone
Journal: Quart. Appl. Math. 72 (2014), 291-310
MSC (2010): Primary 62G07, 41A30
DOI: https://doi.org/10.1090/S0033-569X-2014-01333-4
Published electronically: February 5, 2014
MathSciNet review: 3186238
Full-text PDF

Abstract | References | Similar Articles | Additional Information

Abstract: A kernel method is proposed to estimate the condensed density of the generalized eigenvalues of pencils of Hankel matrices whose elements have a joint noncentral Gaussian distribution with nonidentical covariance. These pencils arise when the complex exponentials approximation problem is considered in Gaussian noise. Several moments problems can be formulated in this framework, and the estimation of the condensed density above is the main critical step for their solution. It is shown that the condensed density satisfies approximately a diffusion equation, which allows us to estimate an optimal bandwidth. It is proved by simulation that good results can be obtained even when the signal-to-noise ratio is so small that other methods fail.

References [Enhancements On Off] (What's this?)

  • [1] Y. Bao and A. Ullah, Expectation of quadratic forms in normal and nonnormal variables with applications, J. Statist. Plann. Inference 140 (2010), no. 5, 1193-1205. MR 2581122 (2011c:62169), https://doi.org/10.1016/j.jspi.2009.11.002
  • [2] P. Barone, A diffusion equation for the density of the ratio of two jointly distributed Gaussian variables and the exponential analysis problem, SIAM J. Sci. Comput. 34 (2012), no. 2, A1053-A1078. MR 2914315, https://doi.org/10.1137/110835323
  • [3] P. Barone, A black box method for solving the complex exponentials approximation problem arXiv:0905.4602v2 (2012), Digital Signal Processing 23 (2013), 49-64.
  • [4] P. Barone, On the condensed density of the generalized eigenvalues of pencils of Gaussian random matrices and applications, J. Multivariate Anal. 111 (2012), 160-173. MR 2944412, https://doi.org/10.1016/j.jmva.2012.05.009
  • [5] P. Barone, Estimation of a new stochastic transform for solving the complex exponentials approximation problem: Computational aspects and applications, Digital Signal Processing 20,3 (2010), 724-735.
  • [6] P. Barone, A new transform for solving the noisy complex exponentials approximation problem, J. Approx. Theory 155 (2008), no. 1, 1-27. MR 2474704 (2010a:62177), https://doi.org/10.1016/j.jat.2008.04.007
  • [7] P. Barone, On the distribution of poles of Padé approximants to the $ Z$-transform of complex Gaussian white noise, J. Approx. Theory 132 (2005), no. 2, 224-240. MR 2118518 (2005h:41028), https://doi.org/10.1016/j.jat.2004.10.014
  • [8] P. Barone, Random matrices in Magnetic Resonance signal processing, The 8-th SIAM Conference on Applied Linear Algebra (2003).
  • [9] P. Barone and R. March, A novel class of Padé based method in spectral analysis, J. Comput. Methods Sci. Eng., 1 (2001), 185-211.
  • [10] P. Barone and R. March, Some properties of the asymptotic location of poles of Padé approximants to noisy rational functions, relevant for modal analysis, IEEE Trans. Signal Process. 46 (1998), no. 9, 2448-2457. MR 1665253 (99m:41023), https://doi.org/10.1109/78.709533
  • [11] P. Barone and A. Ramponi, A new estimation method in modal analysis, IEEE Trans. Signal Process. 48 (2000), no. 4, 1002-1014. MR 1765795, https://doi.org/10.1109/78.827534
  • [12] P. Barone and G. Sebastiani, A new method for Magnetic Resonance image reconstruction with short acquisition time and truncation artifact reduction, IEEE Trans. Medical Imaging, 11 (1992), 250-259.
  • [13] P. Barone and G. Sebastiani, System for reproducing high-resolution magnetic resonance images with a short measurement time, US Patent n.5.646.529, Jul. 8, 1997.
  • [14] Z. I. Botev, J. F. Grotowski, and D. P. Kroese, Kernel density estimation via diffusion, Ann. Statist. 38 (2010), no. 5, 2916-2957. MR 2722460 (2011k:62098), https://doi.org/10.1214/10-AOS799
  • [15] D. Donoho, Superresolution via sparsity constraints, SIAM J. Math. Anal. 23 (1992), no. 5, 1309-1331. MR 1177792 (93f:42023), https://doi.org/10.1137/0523074
  • [16] W. Feller, An introduction to probability theory and its applications. Vol. II, John Wiley & Sons Inc., New York, 1966. MR 0210154 (35 #1048)
  • [17] G. H. Golub, P. Milanfar, and J. Varah, A stable numerical method for inverting shape from moments, SIAM J. Sci. Comput. 21 (1999/00), no. 4, 1222-1243 (electronic). MR 1740393 (2000m:65048), https://doi.org/10.1137/S1064827597328315
  • [18] P. Henrici, Applied and computational complex analysis, Wiley-Interscience [John Wiley & Sons], New York, 1974. Volume 1: Power series--integration--conformal mapping--location of zeros; Pure and Applied Mathematics. MR 0372162 (51 #8378)
  • [19] J. MacQueen, Some methods for classification and analysis of multivariate observations, Proc. Fifth Berkeley Sympos. Math. Statist. and Probability (Berkeley, Calif., 1965/66), Univ. California Press, Berkeley, Calif., 1967, pp. Vol. I: Statistics, pp. 281-297. MR 0214227 (35 #5078)
  • [20] R. March and P. Barone, Application of the Padé method to solving the noisy trigonometric moment problem: Some initial results, SIAM J. Appl. Math. 58 (1998), no. 1, 324-343 (electronic). MR 1610064 (99h:44009), https://doi.org/10.1137/S0036139995268742
  • [21] J. M. Hammersley, The zeros of a random polynomial, Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability, 1954-1955, vol. II, University of California Press, Berkeley and Los Angeles, 1956, pp. 89-111. MR 0084888 (18,941c)
  • [22] R. March and P. Barone, Reconstruction of a piecewise constant function from noisy Fourier coefficients by Padé method, SIAM J. Appl. Math. 60 (2000), no. 4, 1137-1156 (electronic). MR 1760030 (2001b:41018), https://doi.org/10.1137/S0036139998333841
  • [23] M. R. Osborne and G. K. Smyth, A modified Prony algorithm for exponential function fitting, SIAM J. Sci. Comput. 16 (1995), no. 1, 119-138. MR 1311681 (95i:62059), https://doi.org/10.1137/0916008
  • [24] V. Viti, C. Petrucci and P. Barone, Prony methods in NMR spectroscopy, International Journal of Imaging Systems and Technology, 8 (1997), 565-571.
  • [25] J. A. C. Weideman and S. C. Reddy, A MATLAB differentiation matrix suite, ACM Trans. Math. Software 26 (2000), no. 4, 465-519. MR 1939962 (2003g:65004), https://doi.org/10.1145/365723.365727

Similar Articles

Retrieve articles in Quarterly of Applied Mathematics with MSC (2010): 62G07, 41A30

Retrieve articles in all journals with MSC (2010): 62G07, 41A30

Additional Information

Piero Barone
Affiliation: Istituto per le Applicazioni del Calcolo “M. Picone”, C.N.R., Via dei Taurini 19, 00185 Rome, Italy
Email: p.barone@iac.cnr.it, piero.barone@gmail.com

DOI: https://doi.org/10.1090/S0033-569X-2014-01333-4
Keywords: Condensed density, random matrices, parabolic PDE
Received by editor(s): June 20, 2012
Published electronically: February 5, 2014
Article copyright: © Copyright 2014 Brown University
The copyright for this article reverts to public domain 28 years after publication.

American Mathematical Society