Stability of randomized learning algorithms

Journal of Machine Learning Research

Volumn 6, Issue , 2005, Pages

  Elisseeff, Andre ^a   Evgeniou, Theodoros ^b   Pontil, Massimiliano ^c  

^a IBM RESEARCH ZURICH   (Switzerland)

^b INSEAD   (France)

^c UNIVERSITY COLLEGE LONDON   (United Kingdom)

Author keywords

Bagging; Bootstrap methods; Generalization error; Leave one out error; Randomized learning algorithms; Sensitivity analysis; Stability

Indexed keywords

ASYMPTOTIC STABILITY; DATA REDUCTION; ERRORS; PROBLEM SOLVING; RANDOM PROCESSES; SENSITIVITY ANALYSIS;

BAGGING; BOOTSTRAP METHODS; GENERALIZATION ERROR; LEAVE-ONE-OUT ERROR; RANDOMIZED LEARNING ALGORITHMS; SENSITIVITY;

LEARNING ALGORITHMS;

EID: 21844448886     PISSN: 15337928     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (13)

1. Andonova, S., Elisseeff, A., Evgeniou, T., and Pontil, M. (2002), "A simple algorithm to learn stable machines", Proceedings of the 15th European Conference on Artificial Intelligence (ECAI) 2002.
2. Bousquet, O., and Elisseeff, A. (2002), "Stability and generalization", Journal of Machine Learning Research, 2:499-526.
3. Breiman, L. (1996a), "Bagging predictors", Machine Learning, 26(2): 123-140.
4. Breiman, L. (1996b), "Heuristics of instability and stabilization in model selection", Annals of Statistics, 24(6):2350-2383.
5. Devroye, L., Györfi, L., and Lugosi, G. (1996), A Probabilistic Theory of Pattern Recognition, Number 31 in Applications of Mathematics, Springer, New York.
6. Devroye, L., and Wagner, T. (1979), "Distribution-free performance bounds for potential function rules", IEEE Transactions on Information Theory, 25(5):601-604.
7. Evgeniou, T., Pontil, M., and Elisseeff, A. (2004), "Leave-one-out error, stability, and generalization of voting combinations of classifiers", Machine Learning, 55:1, 2004.
8. Kearns, M., and Ron, D. (1999), "Algorithmic stability and sanity check bounds for leave-one-out cross validation bounds", Neural Computation, 11(6): 1427-1453.
9. Kutin, S., and Niyogi, P. (2002), "Almost-everywhere algorithmic stability and generalization error", Uncertainty in Artificial Intelligence (UAI), August, 2002, Edmonton, Canada.
10. McDiarmid, C. (1989), "On the method of bounded differences", In Survey in Combinatorics, p. 148-188. Cambridge University Press, Cambridge.
11. Poggio, T., and Girosi, F. (1990), "Networks for approximation and learning", Proceedings of the IEEE, 78 (9).
12. Poggio, T., Rifkin, R., Mukherjee, S. and Niyogi, P. (2004), "Learning Theory: general conditions for predictivity", Nature, Vol. 428, 419-422.
13. Vapnik, V. (1998), Statistical Learning Theory. Wiley, New York, 1998.