No free lunch for early stopping

Neural Computation

Volumn 11, Issue 4, 1999, Pages 995-1009

  Cataltepe, Zehra ^a   Abu Mostafa, Yaser S ^a   Magdon Ismail, Malik ^b  

^a LUCENT TECHNOLOGIES   (United States)

^b CALIFORNIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; NONLINEAR SYSTEM; PROBABILITY; REPRODUCIBILITY; STATISTICAL MODEL; TIME;

ALGORITHMS; LINEAR MODELS; NONLINEAR DYNAMICS; PROBABILITY; REPRODUCIBILITY OF RESULTS; TIME FACTORS;

EID: 0033561978     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976699300016557     Document Type: Article

References (13)

1. Abu-Mostafa, Y. (1994). Learning from hints. Journal of Complexity, 10, 165-178.
2. Amari, S., Murata, N., Muller, K., Finke, M., & Yang, H. H. (1997). Asymptotic statistical theory of overtraining and cross-validation. IEEE Transactions on Neural Networks, 8(5), 985-996.
3. Baldi, P., & Chauvin, Y. (1991). Temporal evolution of generalization during learning in linear networks. Neural Computation, 3, 589-603.
4. Bishop, C. (1995). Neural networks for pattern recognition, Oxford: Clarendon Press.
5. Dodier, R. (1996). Geometry of early stopping in linear networks. In D. S. Touretzky, M. C. Mozer, & M. E. Hasselmo (Eds.), Advances in neural information processing systems, 8 (pp. 365-371). Cambridge, MA: MIT Press.
6. Goutte, C. (1997). Note on free lunches and cross-validation. Neural Computation, 9(6), 1053-1059.
7. Reed, R. (1993). Pruning algorithms - a survey. IEEE Transactions on Neural Networks, 4(5), 740-747.
8. Sjoberg, J., & Ljung, L. (1995). Overtraining, regularization, and searching for a minimum, with application to neural networks. International Journal of Control, 62(6), 1391-1407.
9. Wang, C., Venkatesh, S. S., & Judd, J. S. (1994). Optimal stopping and effective machine complexity in learning. In J. D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in mural information processing systems, 6 (pp. 303-310). San Mateo, CA: Morgan Kaufmann.
10. Wolpert, D. H. (1995). The Mathematics of generalization: Proceedings of the SFI/CNLS Workshop on Formal Approaches to Supervised Learning. Reading, MA: Addison-Wesley.
11. Wolpert, D. H. (1996a). The existence of a priori distinctions between learning algorithms. Neural Computation, 8(7), 1391-1420.
12. Wolpert, D. H. (1996b). The lack of a priori distinctions between learning algorithms. Neural Computation, 8(7), 1341-1390.
13. Zhu, H., & Rohwer, R. (1996). No free lunch for cross-validation. Neural Computation, 8(7), 1421-1426.