We point out that a number of standard sample complexity bounds (VC-dimension, PAC-Bayes, and others) are all related to the number of bits required to communicate the labels given the unlabeled data for a natural communication game. Motivated by this observation, we give a general sample complexity bound based on this game that allows us to unify these different bounds in one common framework.
CITATION STYLE
Blum, A., & Langford, J. (2003). PAC-MDL bounds. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2777, pp. 344–357). Springer Verlag. https://doi.org/10.1007/978-3-540-45167-9_26
Mendeley helps you to discover research relevant for your work.