CaltechAUTHORS
  A Caltech Library Service

No Free Lunch for Noise Prediction

Magdon-Ismail, Malik (2000) No Free Lunch for Noise Prediction. Neural Computation, 12 (3). pp. 547-564. ISSN 0899-7667. https://resolver.caltech.edu/CaltechAUTHORS:20111128-133815330

[img]
Preview
PDF - Published Version
See Usage Policy.

2546Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20111128-133815330

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.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1162/089976600300015709 DOIUNSPECIFIED
http://www.mitpressjournals.org/doi/abs/10.1162/089976600300015709PublisherUNSPECIFIED
Additional Information:© 2000 Massachusetts Institute of Technology. Received May 29, 1998; accepted March 31, 1999. Posted Online March 13, 2006. We thank Yaser Abu-Mostafa and the members of the Caltech Learning Systems Group for helpful comments. In addition, two anonymous referees provided useful comments.
Issue or Number:3
Record Number:CaltechAUTHORS:20111128-133815330
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20111128-133815330
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:27979
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:28 Nov 2011 22:18
Last Modified:03 Oct 2019 03:28

Repository Staff Only: item control page