A Widely Applicable Bayesian Information Criterion

Preprint English OPEN
Watanabe, Sumio;
  • Subject: Statistics - Machine Learning | Computer Science - Learning
    arxiv: Statistics::Computation

A statistical model or a learning machine is called regular if the map taking a parameter to a probability distribution is one-to-one and if its Fisher information matrix is always positive definite. If otherwise, it is called singular. In regular statistical models, th... View more
Share - Bookmark