Laplace's rule of succession in Information Geometry

DOI10.1007/978-3-319-25040-3_34MaRDI QIDQ2807529zbMATHOpenAlexFDO

Authors Y. Ollivier

Publication date 25 May 2016

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1503.04304

Mathematics Subject Classification ID

Information theory (general) (94A15)

Abstract: Laplace's "add-one" rule of succession modifies the observed frequencies in a sequence of heads and tails by adding one to the observed counts. This improves prediction by avoiding zero probabilities and corresponds to a uniform Bayesian prior on the parameter. The canonical Jeffreys prior corresponds to the "add-one-half" rule. We prove that, for exponential families of distributions, such Bayesian predictors can be approximated by taking the average of the maximum likelihood predictor and the emph{sequential normalized maximum likelihood} predictor from information theory. Thus in this case it is possible to approximate Bayesian predictors without the cost of integrating or sampling in parameter space.

Recommendations

• Information geometry of Bayesian statistics
• A generalization of Jeffreys' rule for non regular models
• <tex>$alpha$</tex>-Parallel Prior and its Properties
• Information geometry and prior selection
• Jeffreys' prior is asymptotically least favorable under entropy risk

This page was built for publication: Laplace's rule of succession in Information Geometry

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2807529)