论文信息 - Test Error Fluctuations in Finite Linear Perceptrons

Test Error Fluctuations in Finite Linear Perceptrons

We examine the fluctuations in the test error induced by random, finite, training and test sets for the linear perceptron of input dimension n with a spherically constrained weight vector. This variance enables us to address such issues as the partitioning of a data set into a test and training set. We find that the optimal assignment of the test set size scales with n2/3.

David Barber | David Saad | Peter Sollich

[1] Vladimir Vapnik,et al. Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2] Sompolinsky,et al. Statistical mechanics of learning from examples. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[3] J. Shao. Linear Model Selection by Cross-validation , 1993 .

[4] William Feller,et al. An Introduction to Probability Theory and Its Applications , 1967 .

[5] David Haussler,et al. Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..

[6] T. Watkin,et al. THE STATISTICAL-MECHANICS OF LEARNING A RULE , 1993 .

[7] D. Saad,et al. FINITE-SIZE EFFECTS AND OPTIMAL TEST SET SIZE IN LINEAR PERCEPTRONS , 1995 .

[8] Shun-ichi Amari,et al. Four Types of Learning Curves , 1992, Neural Computation.

[9] Anders Krogh,et al. Introduction to the theory of neural computation , 1994, The advanced book program.

[10] Lars Kai Hansen,et al. Stochastic linear learning: Exact test and training error averages , 1993, Neural Networks.