
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size
February 1982 (vol. 4 no. 2)
pp. 154157
ASCII Text  x  
Luc Devroye, "Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 4, no. 2, pp. 154157, February, 1982.  
BibTex  x  
@article{ 10.1109/TPAMI.1982.4767222, author = {Luc Devroye}, title = {Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {4}, number = {2}, issn = {01628828}, year = {1982}, pages = {154157}, doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.1982.4767222}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Pattern Analysis and Machine Intelligence TI  Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size IS  2 SN  01628828 SP154 EP157 EPD  154157 A1  Luc Devroye, PY  1982 VL  4 JA  IEEE Transactions on Pattern Analysis and Machine Intelligence ER   
Consider the basic discrimination problem based on a sample of size n drawn from the distribution of (X, Y) on the Borel sets of Rdx {O, 1}. If 0 < R*< is a given number, and 'n  0 is an arbitrary positive sequence, then for any discrimination rule one can find a distribution for (X, Y), not depending upon n, with Bayes probability of error R* such that the probability of error (Rn) of the discrimination rule is larger than R* + 'On for infinitely many n. We give a formal proof of this result, which is a generalization of a result by Cover [1].
Citation:
Luc Devroye, "Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 4, no. 2, pp. 154157, Feb. 1982, doi:10.1109/TPAMI.1982.4767222
Usage of this product signifies your acceptance of the Terms of Use.