Minimum description length
Minimum description length (MDL) is a model selection principle where the shortest description of the data is the best model. MDL methods learn through a data compression perspective and are sometimes described as mathematical applications of Occam's razor. The MDL principle can be extended to other forms of inductive inference and learning, for example to estimation and sequential prediction, without explicitly identifying a single model of the data.
Minimum description length - Wikipedia Jump to content From Wikipedia, the free encyclopedia Model selection principle Minimum description length ( MDL ) is a model selection principle where the shortest description of the data is the best model. MDL methods learn through a data compression perspective and are sometimes described as mathematical applications of Occam's razor . The MDL principle can be extended to other forms of inductive inference and learning, for example to estimation and sequential prediction, without explicitly identifying a single model of the data. MDL has its origins mo
Explore this link on the map →related reading
- Visual Information Theory -- colah's blogcolah.github.io
- [2309.10668] Language Modeling Is Compressionarxiv.org
- Rediscovery of Interiority in MLdanburfoot.net
- Occam’s Razorreadthesequences.com
- deeplearningbook.org/contents/ml.htmldeeplearningbook.org
- Solomonoff's theory of inductive inference - Wikipediaen.wikipedia.org
- Gregory Gundersengregorygundersen.com
- Machine learning - Wikipediaen.wikipedia.org
- Minimum redundancy feature selection - Wikipediaen.wikipedia.org
- "Occam"-style Bounds for Long Programsbactra.org
- Data Compression Explainedmattmahoney.net
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai