Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension
From MaRDI portal
Publication:1314506
zbMath0798.68145MaRDI QIDQ1314506
David Haussler, Michael Kearns, Robert E. Schapire
Publication date: 3 March 1994
Published in: Machine Learning (Search for Journal in Brave)
Bayesian learningVC dimensionstatistical physicsinformation theorylearning curvesaverage-case learning
Related Items
Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension, Learning from a population of hypotheses, Characterizing rational versus exponential learning curves, Mutual information, metric entropy and cumulative relative entropy risk, MetaBayes: Bayesian Meta-Interpretative Learning Using Higher-Order Stochastic Refinement, Rigorous learning curve bounds from statistical mechanics, Learning a priori constrained weighted majority votes, QG/GA: a stochastic search for Progol, Sample size lower bounds in PAC learning by Algorithmic Complexity Theory, Bayesian predictiveness, exchangeability and sufficientness in bacterial taxonomy, Query by committee, linear separation and random walks.
