What is MDL?

The purpose of statistical modeling is to discover regularities in observed data. The success in finding such regularities can be measured by the length with which the data can be described. This is the rationale behind the Minimum Description Length (MDL) Principle introduced by Jorma Rissanen (Rissanen, 1978).

'' The MDL Principle is a relatively recent method for inductive inference. The fundamental idea behind the MDL Principle is that any regularity in a given set of data can be used to compress the data, i.e. to describe it using fewer symbols than needed to describe the data literally. '' (Grünwald, 1998)

What is mdl-research.org?

Minimum Description Length on the Web is intended as a source of information for everyone who wants to know more about MDL. The site contains links and references to suggested reading, tutorials, lecture notes, etc. on MDL as well as links to people who are working on MDL and related topics.

	The Reading section contains references to selected papers, books, lecture material, etc., and links to journals and conferences.
	The Demonstrations section illustrates MDL through on-line demonstrations, and provides links to software on the web.
	The People section has links to researchers who are working on MDL and related fields. You can find lots of useful information on their homepages.
	The Related Topics section is a short collection of links to MDL related topics, such as information theory, Bayesian statistics, and learning theory.
	If you have any comments on this site please do not hesitate to give us Feedback.

News & Events

February 3, 2006. Jorma Rissanen receives the Kolmogorov medal and gives the 4th Annual Kolmogorov Lecture at Royal Holloway, Univ. London. »»» slides

January 10-13, 2007. Conference on Logic, Computability and Randomness, Buenos Aires, Argentina.

January 26, 2007. A book by Jorma Rissanen has appeared. See the Reading section.

January 29-February 2, 2007. 2007 Information Theory and Applications (ITA) Workshop, San Diego, California.

March 1, 2007. EURASIP JBSB Special Issue on Information Theoretic Methods for Bioinformatics, submission deadline.

June, 2007. A book by Peter Grünwald appears. See the Reading section for a sample chapter.

June 24-29, 2007. IEEE International Symposium on Information Theory, Nice, France.

January 27-February 1, 2008. 2008 Information Theory and Applications Workshop, San Diego, USA.

May 5-9, 2008. IEEE Information Theory Workshop, Porto, Portugal.

July 6-11, 2008. IEEE International Symposium on Information Theory, Toronto, Canada.

July 9-12, 2008. Three major conferences, UAI, ICML, and COLT, in Helsinki, Finland.

July 9, 2008. ICML/UAI/COLT Workshop: Recent Breakthroughts in MDL Learning, Helsinki, Finland.

July 14-15, 2008. Information Theory and Statistical Learning, Las Vegas, Nevada.