论文信息 - A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

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.

Manfred Opper | Dörthe Malzahn | M. Opper | D. Malzahn

[1] M. Mézard,et al. Spin Glass Theory and Beyond , 1987 .

[2] M. Opper,et al. Advanced mean field methods: theory and practice , 2001 .

[3] M. Chavance. [Jackknife and bootstrap]. , 1992, Revue d'epidemiologie et de sante publique.

[4] H. Nishimori. Statistical Physics of Spin Glasses and Information Processing , 2001 .

[5] Christian Van den Broeck,et al. Statistical Mechanics of Learning , 2001 .

[6] Manfred Opper,et al. A Variational Approach to Learning Curves , 2001, NIPS.

[7] Geoffrey E. Hinton,et al. Bayesian Learning for Neural Networks , 1995 .

[8] R. Feynman,et al. Quantum Mechanics and Path Integrals , 1965 .

[9] 西森秀稔. Statistical physics of spin glasses and information processing : an introduction , 2001 .

[10] Lehel Csató,et al. Sparse On-Line Gaussian Processes , 2002, Neural Computation.