Risk bounds for kernel density estimators


We use results from probability on Banach spaces and Poissonization techniques to develop sharp finite sample and asymptotic moment bounds for the L p risk for kernel density estimators. Our results are shown to augment the previous work in this area. Bibliography: 19 titles.


Banach Space Kernel Density Density Estimator Finite Sample Kernel Density Estimator 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    P. Billingsley, Convergence of Probability Measures, Wiley, New York (1968).MATHGoogle Scholar
  2. 2.
    J. Bretagnolle and C. Huber, “Estimation des densités: risque minimax,” Z. Wahrsch. Verw. Gebiete, 47, 119–137 (1979).CrossRefMathSciNetGoogle Scholar
  3. 3.
    L. Devroye, “On arbitrarily slow rates of global convergence in density estimation,” Z. Wahrsch. Verw. Gebiete, 62, 475–483 (1983).CrossRefMathSciNetMATHGoogle Scholar
  4. 4.
    L. Devroye, A Course in Density Estimation, Progress in Probability and Statistics, 14, Birkhäuser, Boston (1987).MATHGoogle Scholar
  5. 5.
    L. Devroye, “A note on the usefulness of superkernels in density estimation,” Ann. Statist., 20, 2037–2056 (1992).CrossRefMathSciNetMATHGoogle Scholar
  6. 6.
    L. Devroye and L. Györfi, Nonparametric Density Estimation: The L 1 View, Wiley, New York (1985).MATHGoogle Scholar
  7. 7.
    S. Yu. Efroimovich and M. S. Pinsker, “Estimation of square-integrable probability density of a random variable,” Probl. Inform. Transmission, 18, 175–189 (1982).MathSciNetGoogle Scholar
  8. 8.
    G. B. Folland, Real Analysis, Wiley, New York (1984).MATHGoogle Scholar
  9. 9.
    E. Giné, A. Zaitsev, and D. M. Mason, “The L 1-norm density estimator process,” Ann. Probab., 31, 719–768 (2003).CrossRefMathSciNetMATHGoogle Scholar
  10. 10.
    E. Guerre and A. Tsybakov, “Exact asymptotic minimax constants for the estimation of analytical functions in L p,” Probab. Theory Related Fields, 112, 33–51 (1998).CrossRefMathSciNetMATHGoogle Scholar
  11. 11.
    R. Hasminskii and I. Ibragimov, “On density estimation in the view of Kolmogorov’s ideas in approximation theory,” Ann. Statist., 18, 999–1010 (1990).CrossRefMathSciNetGoogle Scholar
  12. 12.
    I. Ibragimov and R. Hasminskii, “On estimation of the density function,” Zap. Nauchn. Sem. LOMI, 98, 61–85 (1990).MathSciNetGoogle Scholar
  13. 13.
    I. Ibragimov and R. Hasminskii, “An estimate of the density of a distribution belonging to a class of entire functions,” Teor. Veroyatn. Primen., 27, 514–524 (1982).MATHGoogle Scholar
  14. 14.
    W. B. Johnson, G. Schechtman, and J. Zinn, “Best constants in moment inequalities for linear combinations of independent and exchangeable random variables,” Ann. Probab. 13, 234–253 (1985).CrossRefMathSciNetMATHGoogle Scholar
  15. 15.
    M. Schipper, “Optimal rates and constants in L 2-minimax estimation of probability density functions,” Math. Methods Statist., 5, 253–274 (1996).MathSciNetMATHGoogle Scholar
  16. 16.
    G. R. Shorack and J. A. Wellner, Empirical Processes with Applications to Statistics, John Wiley & Sons, New York (1986).MATHGoogle Scholar
  17. 17.
    E. M. Stein, Singular Integrals and Differentiability Properties of Functions, Princeton Univ. Press, New Jersey (1970).MATHGoogle Scholar
  18. 18.
    T. J. Sweeting, “Speeds of convergence in the multidimensional central limit theorem,” Ann. Probab., 5, 28–41 (1977).CrossRefMathSciNetMATHGoogle Scholar
  19. 19.
    M. Talagrand, “Isoperimetry and integrability of the sum of independent Banach-space valued random variables,” Ann. Probab., 17, 1546–1570 (1989).CrossRefMathSciNetMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, Inc. 2009

Authors and Affiliations

  1. 1.Statistics ProgramUniversity of DelawareNewarkUSA

Personalised recommendations