Sciweavers

TIT
1998

The Minimum Description Length Principle in Coding and Modeling

13 years 4 months ago
The Minimum Description Length Principle in Coding and Modeling
—We review the principles of Minimum Description Length and Stochastic Complexity as used in data compression and statistical modeling. Stochastic complexity is formulated as the solution to optimum universal coding problems extending Shannon’s basic source coding theorem. The normalized maximized likelihood, mixture, and predictive codings are each shown to achieve the stochastic complexity to within asymptotically vanishing terms. We assess the performance of the minimum description length criterion both from the vantage point of quality of data compression and accuracy of statistical inference. Context tree modeling, density estimation, and model selection in Gaussian linear regression serve as examples.
Andrew R. Barron, Jorma Rissanen, Bin Yu
Added 23 Dec 2010
Updated 23 Dec 2010
Type Journal
Year 1998
Where TIT
Authors Andrew R. Barron, Jorma Rissanen, Bin Yu
Comments (0)