Synonyms
Definition
The original “general” minimum description length (MDL) principle for estimation of statistical properties in observed data y n, or the modelf(y n; θ, k), represented by parameters θ = θ 1, …, θ k , can be stated thus,
“Find the model with which observed data and the model can be encoded with shortest code length”:
$$\min _{\theta ,k}\;[\,\log 1/f({y}^{n};\theta ,k) + L(\theta ,k)],$$
where L(θ, k) denotes the code length for the parameters.
The principle is very general and produces a model defined by the estimated parameters. It leaves the selection of L(θ, k) open, and in complex applications the code length can be calculated by visualizing a coding process. The only requirement is that the data must be decodable.
Motivation and Background
The MDL principle is based on the fact that it is not possible to compress data well without taking advantage of the regular features in them. Hence, estimation and data...
Recommended Reading
Grünwald, P. D. (2007). The minimum description length principle (703 pp.). Cambridge/London: The MIT Press.
Rissanen, J. (2007). Information and complexity in statistical modeling (142 pp.). Springer: New York.
Rissanen, J. (September 2009). Optimal estimation. IEEE Information Theory Society Newsletter, 59(3).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
Rissanen, J. (2011). Minimum Description Length Principle. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_540
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_540
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30768-8
Online ISBN: 978-0-387-30164-8
eBook Packages: Computer ScienceReference Module Computer Science and Engineering