Abstract
It is known theoretically that an algorithm cannot be good for an arbitrary prior. We show that in practical terms this also applies to the technique of ``cross validation'', which has been widely regarded as defying this general rule. Numerical examples are analysed in detail. Their implications to researches on learning algorithms are discussed.
Original language | English |
---|---|
Pages (from-to) | 1421-1426 |
Number of pages | 6 |
Journal | Neural Computation |
Volume | 8 |
Issue number | 7 |
DOIs | |
Publication status | Published - 1 Oct 1996 |
Bibliographical note
Copyright of the Massachusetts Institute of Technology Press (MIT Press)Keywords
- learning algorithms
- cross validation