- Tytuł:
- Probabilities of discrepancy between minima of cross-validation, Vapnik bounds and true risks
- Autorzy:
- Klęsk, P.
- Powiązania:
- https://bibliotekanauki.pl/articles/929593.pdf
- Data publikacji:
- 2010
- Wydawca:
- Uniwersytet Zielonogórski. Oficyna Wydawnicza
- Tematy:
-
estymacja regresji
walidacja krzyżowa
teoria uczenia się
generalizacja
teoria statystyczna
regression estimation
model comparison
complexity selection
cross-validation
generalization
statistical learning theory
generalization bounds
structural risk minimization - Opis:
- Two known approaches to complexity selection are taken under consideration: n-fold cross-validation and structural risk minimization. Obviously, in either approach, a discrepancy between the indicated optimal complexity (indicated as the minimum of a generalization error estimate or a bound) and the genuine minimum of unknown true risks is possible. In the paper, this problem is posed in a novel quantitative way. We state and prove theorems demonstrating how one can calculate pessimistic probabilities of discrepancy between these minima for given for given conditions of an experiment. The probabilities are calculated in terms of all relevant constants: the sample size, the number of cross-validation folds, the capacity of the set of approximating functions and bounds on this set. We report experiments carried out to validate the results.
- Źródło:
-
International Journal of Applied Mathematics and Computer Science; 2010, 20, 3; 525-544
1641-876X
2083-8492 - Pojawia się w:
- International Journal of Applied Mathematics and Computer Science
- Dostawca treści:
- Biblioteka Nauki
Artykuł