nips nips2002 nips2002-17 nips2002-17-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Dörthe Malzahn, Manfred Opper
Abstract: We apply the replica method of Statistical Physics combined with a variational method to the approximate analytical computation of bootstrap averages for estimating the generalization error. We demonstrate our approach on regression with Gaussian processes and compare our results with averages obtained by Monte-Carlo sampling.
[1] A. Engel and C. Van den Broeck, Statistical Mechanics of Learning (Cambridge University Press, 2001).
[2] H. Nishimori, Statistical Physics of Spin Glasses and Information Processing (Oxford Science Publications, 2001).
[3] B. Efron and R. J. Tibshirani, An Introduction to the Bootstrap, Monographs on Statistics and Applied Probability 57 (Chapman Hall, 1993).
[4] M. M´ zard, G. Parisi, and M. A. Virasoro, Spin Glass Theory and Beyond, Lecture e Notes in Physics 9 (World Scientific, 1987). ¢
[5] J. Shao and D. Tu, The Jackknife and Bootstrap, Springer Series in Statistics (Springer Verlag, 1995).
[6] D. Malzahn and M. Opper, A variational approach to learning curves, NIPS 14, Editors: T.G. Dietterich, S. Becker, Z. Ghahramani, (MIT Press, 2002).
[7] R. Neal, Bayesian Learning for Neural Networks, Lecture Notes in Statistics 118 (Springer, 1996).
[8] R. P. Feynman and A. R. Hibbs, Quantum mechanics and path integrals (Mc GrawHill Inc., 1965).
[9] L. Csat´ and M. Opper, Sparse Gaussian Processes, Neural Computation 14, No 3, o 641 - 668 (2002).
[10] M. Opper and D. Saad (editors), Advanced Mean Field Methods: Theory and Practice, (MIT Press, 2001).
[11] From http://www1.ics.uci.edu/ mlearn/MLSummary.html. The data set contains 4177 examples. We used a representative fraction (the forth block (a 1000 data) from the list). £