Bayesian Approximation Theory

David J C MacKay

Given that a learning algorithm achieves a training error \ensuremath{\hat{\epsilon}_{\rm M}} on its training set, what do we expect its test error to be? This is an inference problem (``Given A, predict B") so it must have a Bayesian answer. This note discusses the forward model and prior required to get sensible answers.

postscript (Cambridge UK).

postscript (Canada mirror).

pdf (Cambridge UK).

pdf (Canada mirror).

All postscript files are compressed with gzip - see this page for advice about gzip, if needed.


related publications.
David MacKay's: home page, publications. bibtex file.
Canadian mirrors: home page, publications. bibtex file.