Math 2.0

Statistics Model selection Concept

Minimum description length

Summary

The minimum description length (MDL) principle selects the model that gives the shortest description of the data. The description counts the bits to state the model and the bits to encode the data with the help of the model. It turns model selection into data compression: a good model captures regularities and so compresses the data. It is a computable relative of Kolmogorov complexity, and Jorma Rissanen introduced it.

Further reading

  1. Web https://en.wikipedia.org/wiki/Minimum_description_length
About this page
Tag8JV9PPFRG4
URIm2://8JV9PPFRG4
Kindconcept
WritingW0 stub
MSC62B10, 94A17, 68Q30
Same as

Markdown · JSON · Edit on GitHub

What this page needs for W1

  • an inventory row: the row of the inventory that the node accounts for (0 of 1)
  • a source with a locator (0 of 1)

The writing levels say how complete the text of a page is. They do not measure its truth.

What links here

Definitions