Bayesian and quasi-Bayesian estimators for mutual information from discrete data

Evan Archer, Il Memming Park, Jonathan William Pillow

Research output: Contribution to journalArticlepeer-review

39 Scopus citations


Mutual information (MI) quantifies the statistical dependency between a pair of random variables, and plays a central role in the analysis of engineering and biological systems. Estimation of MI is difficult due to its dependence on an entire joint distribution, which is difficult to estimate from samples. Here we discuss several regularized estimators for MI that employ priors based on the Dirichlet distribution. First, we discuss three "quasi-Bayesian" estimators that result from linear combinations of Bayesian estimates for conditional and marginal entropies. We show that these estimators are not in fact Bayesian, and do not arise from a well-defined posterior distribution and may in fact be negative. Second, we show that a fully Bayesian MI estimator proposed by Hutter (2002), which relies on a fixed Dirichlet prior, exhibits strong prior dependence and has large bias for small datasets. Third, we formulate a novel Bayesian estimator using a mixture-of-Dirichlets prior, with mixing weights designed to produce an approximately flat prior over MI. We examine the performance of these estimators with a variety of simulated datasets and show that, surprisingly, quasi-Bayesian estimators generally outperform our Bayesian estimator. We discuss outstanding challenges for MI estimation and suggest promising avenues for future research.

Original languageEnglish (US)
Pages (from-to)1738-1755
Number of pages18
Issue number5
StatePublished - May 2013

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Mathematical Physics
  • Physics and Astronomy (miscellaneous)
  • Electrical and Electronic Engineering


  • Bayes least squares
  • Dirichlet distribution
  • Entropy
  • Mutual information


Dive into the research topics of 'Bayesian and quasi-Bayesian estimators for mutual information from discrete data'. Together they form a unique fingerprint.

Cite this