Bias of Nearest Neighbor Error Estimates

  title={Bias of Nearest Neighbor Error Estimates},
  author={Keinosuke Fukunaga and Donald M. Hummels},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
The bias of the finite-sample nearest neighbor (NN) error from its asymptotic value is examined. Expressions are obtained which relate the bias of the NN and 2-NN errors to sample size, dimensionality, metric, and distributions. These expressions isolate the effect of sample size from that of the distributions, giving an explicit relation showing how the bias changes as the sample size is increased. Experimental results are given which suggest that the expressions accurately predict the bias… CONTINUE READING
Highly Cited
This paper has 56 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 37 extracted citations

56 Citations

Citations per Year
Semantic Scholar estimates that this publication has 56 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 18 references

Rates of convergence for nearest neighbor procedures

  • T. M. Cover
  • Proc. Hawaii Int. Conf. Syst. Sci., 1968, pp. 413…
  • 1968
Highly Influential
5 Excerpts

The rate of convergence of k.-NN regression estimates and classification rules

  • L. Gy6rfi
  • IEEE Trans. Inform. Theory, vol. IT-27, pp. 362…
  • 1981

Distribution free consistency results for nonparametric discrimination and regression function estimation

  • L. Devroye, T. J. Wagner
  • Ann. Stat., vol. 8, pp. 231-239, 1980.
  • 1980
1 Excerpt

The exponential rate of convergence of error for k.-NN nonparametric regression and decision

  • J. Beck
  • Prob. Contr. Inforrn. Theory, vol. 8, pp. 303-311…
  • 1979

Similar Papers

Loading similar papers…