Summary: No Free Lunch For Noise Prediction
Malik Magdon­Ismail
Caltech 136­93
Pasadena, CA 91125
magdon@cco.caltech.edu
February 20, 2000
-- Neural Computation, Vol 12, No. 3, 2000 --
Abstract
No Free Lunch theorems have shown that learning algorithms
cannot be universally good. We show that No Free Lunch exists
for noise prediction as well. We show that when the noise is ad­
ditive and the prior over target functions is ``uniform'', a prior on
the noise distribution cannot be updated, in the Bayesian sense,
from any finite data set. We emphasize the importance of a prior
over the target function in order to justify superior performance
for learning systems.
Keywords: No Free Lunch, Noise Prediction, Bayesian Prior.
1

Which data set has more noise?

Source: Abu-Mostafa, Yaser S. - Department of Mechanical Engineering & Computer Science Department, California Institute of Technology

Collections: Computer Technologies and Information Sciences