PAC-Bayesian Theory

David McAllester, Takintayo AkinbiyiEmpirical Inference 2013 · OpenReview

Abstract

The PAC-Bayesian framework is a frequentist approach to machine learning which encodes learner bias as a “prior probability” over hypotheses. This chapter reviews basic PAC-Bayesian theory, including...
BibTeX
@inproceedings{mcallester2013pac,
  author = {David McAllester and Takintayo Akinbiyi},
  title = {{PAC-Bayesian Theory}},
  booktitle = {Empirical Inference},
  year = {2013},
  url = {https://openreview.net/forum?id=QBOf1VVtLq},
}

Loading related content...

Figure