On-line versus Off-line Learning from Random Examples: General Results
- 25 November 1996
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 77 (22) , 4671-4674
- https://doi.org/10.1103/physrevlett.77.4671
Abstract
I propose a general model of on-line learning from random examples which, when applied to a smooth realizable stochastic rule, yields the same asymptotic generalization error rate as optimal batch algorithms. The approach is based on an iterative Gaussian approximation to the posterior Gibbs distribution of rule parameters.Keywords
This publication has 14 references indexed in Scilit:
- On-line Gibbs LearningPhysical Review Letters, 1996
- Unsupervised Learning by Examples: On-line versus Off-linePhysical Review Letters, 1996
- Learning from noisy data: An exactly solvable modelPhysical Review E, 1995
- Local and Global Convergence of On-Line LearningPhysical Review Letters, 1995
- On-line learning in the committee machineJournal of Physics A: General Physics, 1995
- On-Line Learning with a PerceptronEurophysics Letters, 1994
- The statistical mechanics of learning a ruleReviews of Modern Physics, 1993
- Optimal generalization in perceptionsJournal of Physics A: General Physics, 1992
- Statistical mechanics of learning from examplesPhysical Review A, 1992
- Statistical Decision Theory and Bayesian AnalysisPublished by Springer Nature ,1985