论文信息 - Regression with Gaussian Processes: Average Case Performance

Regression with Gaussian Processes: Average Case Performance

Recently, new models for regression and classification have been introduced which may be interpreted as neural networks in the limit of infinitely many parameters. For a regression model, the average case generalization performance is studied using a combination of information theoretic ideas and statistical mechanics methods.

M. Opper

[1] Physical Review , 1965, Nature.

[2] M. V. Rossum,et al. In Neural Computation , 2022 .

[3] Carl E. Rasmussen,et al. In Advances in Neural Information Processing Systems , 2011 .

[4] David Barber,et al. Gaussian Processes for Bayesian Classification via Hybrid Monte Carlo , 1996, NIPS.

[5] D. Haussler,et al. MUTUAL INFORMATION, METRIC ENTROPY AND CUMULATIVE RELATIVE ENTROPY RISK , 1997 .

[6] Vladimir Cherkassky,et al. The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[7] Manfred Opper,et al. Statistical mechanics of generalization , 1998 .

[8] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.