Abstract
An important problem in nonparametric regression is to control the amount of smoothing in the regression, which in turn is specified by the so-called bandwidth parameter. The problem has received much attention in the statistics literature, leading to a variety of methods for bandwidth selection. Most methods arrive at an empirical risk estimate by partitioning the data into two sets: training samples and testing samples. The training samples are used to compute a family of regression functions indexed by their bandwidths. The optimal bandwidth is chosen as the value for which the regression function minimizes the quadratic empirical risk on the training sample. In this paper, we propose to select the bandwidth within the framework of minimum mean-squared-error (MMSE) estimation. Since the oracle MSE cannot be computed in practice due to non-availability of the ground truth, we propose to employ an unbiased estimator of the MSE. Specifically, we rely on the Stein’s unbiased risk estimator (SURE) to optimize for the bandwidth parameter. We address the problems of kernel regression and local polynomial regression (LPR) within a common framework and show that SURE provides a good approximation to the oracle MSE, especially with larger data lengths, thus helping us in arriving at the MMSE solution. As a specific application, we address the problem of signal reconstruction from noisy nonuniform samples in both one and two dimensions. For a smooth progression of the exposition, we also provide certain results in the uniform sampling case, before proceeding with the case of nonuniform sampling.
Similar content being viewed by others
References
A. Benazza-Benyahia and J.-C. Pesquet, Building Robust Wavelet Estimators for Multicomponent Images Using Stein’s Principle, IEEE Trans. Image Process., 14, 1814–1830, 2005.
T. Blu and F. Luisier, The SURE-LET Approach to Image Denoising, IEEE Trans. Image Process., 16, 2778–2786, 2007.
M. Brockmann, T. Gasser, E. Herrmann, Locally Adaptive Bandwidth Choice for Kernel Regression Estimators, J. Amer. Statist. Assoc., 88, 1302–1309, 1993.
W. S. Cleveland, Robust Locally Weighted Regression and Smoothing Scat-terplots, J. Amer. Statist. Assoc., 74, 829–836, 1979.
D. L. Donoho and I. M. Johnstone, Adapting to Unknown Smoothness via Wavelet Shrinkage, J. Amer. Stat. Assoc., 90, 1200–1224, 1995.
Y. C. Eldar, Generalized SURE for Exponential Families: Applications to Regularization, IEEE Trans. Signal Process., 57, 471–481, 2009.
J. Fan and I. Gijbels, Variable Bandwidth and Local Linear Regression Smoothers, Ann. Stat., 20, 2008–2036, 1992.
J. Fan and I. Gijbels, Data-Driven Bandwidth Selection in Local Polynomial Fitting: Variable Bandwidth and Spatial Adaptation, J. Roy. Statist. Soc. Ser. B, 57, 371–394, 1995.
J. Fan and I. Gijbels, Adaptive Order Polynomial Fitting: Bandwidth Ro-bustification and Bias Reduction, J. Comput. Graph. Statist., 4, 213–227, 1995.
J. Fan and I. Gijbels, Local Polynomial Modelling and Its Applications, Chapman and Hall, New York, 1996.
J. Fan, I. Gijbels, T-C Hu, and L-S Huang, A Study of Variable Bandwidth Selection for Local Polynomial Regression, Statistica Sinica, 6, 113–127, 1996.
J. Fan, N. E. Heckman, and M. P. Wand, Local Polynomial Kernel Regression for Generalized Linear Models and Quasi-Likelihood Functions, J. Amer. Statist. Assoc., 90, 141–150, 1995.
R. Giryes, M. Elad, and Y. C. Eldar, The Projected GSURE for Automatic Parameter Tuning in Iterative Shrinkage Methods, Appl. Comput. Harmon. Anal., 30, 407–422, 2011.
W. Hardle, Applied Nonparametric Regression, Cambridge University Press, Cambridge, 1990.
W. Hardle, M. Muller, S. Sperlich, and A. Werwatz, Nonparametric and Semiparametric Models, Springer, New York, 2004.
N. W. Hengartner and M. H.Wegkamp, Bandwidth Selection for Local Linear Regression Smoothers, J. R. Statist. Soc. B, 64, Part 4, 791–804, 2002.
E. Herrmann, Local Bandwidth Choice in Kernel Regression Estimation, J. Comput. Graph. Statist., 6, 35–54, 1997.
V. Katkovnik and L. Stankovic, Instantaneous Frequency Estimation Using the Wigner Distribution With Varying and Data-Driven Window Length, IEEE Trans. Signal Process., 46, 2315–2325, 1998.
H. Kishan and C. S. Seelamantula, SURE-Fast Bilateral Filters, Proc. IEEE Intl. Conf. on Acoust., Speech and Signal Process., 1129–1132, March 2012.
F. Luisier, T. Blu, and M. Unser, A New SURE Approach to Image Denoising: Interscale Orthonormal Wavelet Thresholding, IEEE Trans. Image Process., 16, 593–606, 2007.
F. Luisier, C. Vonesch, T. Blu, and M. Unser, Fast Interscale Wavelet Denoising of Poisson-Corrupted Images, Signal Process., 90, 415–427, 2010.
N. R. Muraka and C. S. Seelamantula, A Risk-Estimation-Based Comparison of Mean Square Error and Itakura-Saito Distortion Measures for Speech Enhancement, in Proc. Interspeech, Florence, 349–352, 2011.
J.-C. Pesquet and D. Leporini, A New Wavelet Estimator for Image De-noising, in Proc. Sixth Int. Conf. Image Process. and Its Applicat., Dublin, 249–253, 1997.
W. H. Press, S. A. Teukolsky, W. T. Vetterling, B. P. Flannery, Numerical Recipes: The Art of Scientific Computing, Cambridge University Press, New York, 2007.
S. Ramani, T. Blu, and M. Unser, Monte Carlo SURE: A Black-Box Optimization of Regularization Parameters for General Denoising Algorithms, IEEE Trans. Image Process., 17, 1540–1554, 2008.
L. I. Rudin, S. Osher, and E. Fatemi, Nonlinear Total Variation Based Noise Removal Algorithms, Physica D, 60, 259–268, 1992.
D. Ruppert and M. P. Wand, Multivariate Locally Weighted Least Squares Regression, Ann. Stat., 22, 1346–1370, 1994.
A. Savitzky and M. J. E. Golay, Smoothing and Differentiation of Data by Simplified Least Squares Procedures, Anal. Chem., 36, 1627–1639, 1964.
R. W. Schafer, What is a Savitzky-Golay Filter?, IEEE Signal Process. Mag., 28, 111–117, 2011.
W. R. Schucany, Adaptive Bandwidth Choice for Kernel Regression, J. Amer. Statist. Assoc., 90, 535–540, 1995.
B. W. Silverman, Density Estimation for Statistics and Data Analysis, Chapman and Hall, New York, 1986.
C. M. Stein, Estimation of the Mean of a Multivariate Normal Distribution, Ann. Stat., 9, 1135–1151, 1981.
C. J. Stone, Consistent Nonparametric Regression, Ann. Stat., 5, 595–620, 1977.
H. Takeda, S. Farsiu, and P. Milanfar, Kernel Regression for Image Processing and Reconstruction, IEEE Trans. Image Process., 16, 349–366, 2007.
P. Vieu, Nonparametric Regression: Optimal Local Bandwidth Choice, J. Roy. Statist. Soc. Ser. B, 53, 453–464, 1991.
G. Wahba, “Spline models for observational data,” Chapter 4, 45–65, CBMS-NSF Regional Conf. Series in Appl. Math. Soc. Ind. Appl. Math., Philadelphia, PA, 1990.
M. P. Wand and M. C. Jones, Kernel Smoothing, Chapman and Hall, New York, 1995.
J. Zhang and A. Liu, Local Polynomial Fitting Based on Empirical Likelihood, Bernoulli, 9, 579–605, 2003.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Krishnan, S.R., Seelamantula, C.S. SURE-Optimal Bandwidth Selection in Nonparametric Regression. STSIP 11, 133–163 (2012). https://doi.org/10.1007/BF03549553
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF03549553