DMCA
The Lack of A Priori Distinctions Between Learning Algorithms (1996)
| Citations: | 166 - 5 self |
BibTeX
@MISC{Wolpert96thelack,
author = {David H. Wolpert},
title = {The Lack of A Priori Distinctions Between Learning Algorithms},
year = {1996}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This is the first of two papers that use off-training set (OTS) error to investigate the assumption -free relationship between learning algorithms. This first paper discusses the senses in which there are no a priori distinctions between learning algorithms. (The second paper discusses the senses in which there are such distinctions.) In this first paper it is shown, loosely speaking, that for any two algorithms A and B, there are "as many" targets (or priors over targets) for which A has lower expected OTS error than B as vice-versa, for loss functions like zero-one loss. In particular, this is true if A is cross-validation and B is "anti-cross-validation" (choose the learning algorithm with largest cross-validation error). This paper ends with a discussion of the implications of these results for computational learning theory. It is shown that one can not say: if empirical misclassification rate is low; the Vapnik-Chervonenkis dimension of your generalizer is small; and the trainin...
Keyphrases
priori distinction learning algorithm first paper many target cross-validation error loss function computational learning theory learning algorithm priori distinction ots error zero-one loss off-training set vapnik-chervonenkis dimension assumption free relationship second paper empirical misclassification rate
