The Relationship Between PAC, the Statistical Physics Framework, the Bayesian Framework, and the VC Framework

A comparison of GCV and GML for choosing the smoothing parameter in the generalized spline smoothing problem. Wolpert, D. (1994d). How good generalizers need to be: beyond bias plus variance. In preparation. Wolpert, D. (1994e). On exhaustive learning. These proceedings. Wolpert, D. (1994f). On overfitting avoidance as bias. In preparation. Wolpert, D. (1994g). On the Bayesian " Occam factors " argument for Occam's razor. Calculation of the learning curve of Bayes optimal classification algorithm for learning a perceptron with noise. Technical report. Perrone, M. (1993). Improving regression estimation: averaging methods for variance reduction with extensions to general convex measure optimization. Ph. Haussler, D. (1994a). Decision theoretic generalizations of the PAC model for neural net and other learning applications. These proceedings. Haussler, D. (1994b). The probably approximately correct (PAC) and other learning models. Chapter 9 from Foundations of knowledge acquisition: Machine Learning, A. Meyrowitz and S. Chip-man (Ed.'s). Kluwer. MacKay D. (1992). Information-based objective functions for active data selection. Neural Computation. 4, 590-604. MAXENT. Maximum Entropy and Bayesian Methods. Many years and editors. Moody, J. (1992). The effective number of parameters: an analysis of generalization and regular-ization in nonlinear learning systems.