We show that forms of Bayesian and MDL inference that are often applied to classification problems can be inconsistent. This means there exists a learning problem such that for all amounts of data the generalization errors of the MDL classifier and the Bayes classifier relative to the Bayesian posterior both remain bounded away from the smallest achievable generalization error.
CITATION STYLE
Grünwald, P., & Langford, J. (2004). Suboptimal behavior of bayes and MDL in classification under misspecification. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3120, pp. 331–347). Springer Verlag. https://doi.org/10.1007/978-3-540-27819-1_23
Mendeley helps you to discover research relevant for your work.