Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

March 1, 2000, Vol. 12, No. 3, Pages 547-564
(doi: 10.1162/089976600300015709)
© 2000 Massachusetts Institute of Technology
No Free Lunch for Noise Prediction
Article PDF (266.71 KB)
Abstract

No-free-lunch theorems have shown that learning algorithms cannot be universally good. We show that no free funch exists for noise prediction as well. We show that when the noise is additive 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.