## Universal Modeling: Introduction to modern MDL

author: Peter Grünwald, Center for Mathematics and Computer Science - CWI
published: Feb. 25, 2007,   recorded: August 2003,   views: 913
Categories
You might be experiencing some problems with Your Video player.

# Slides

0:00 Slides Universal Modeling: Introduction to ‘Modern’ MDL Minimum Description Length Principle Minimum Description Length Principle Minimum Description Length Principle Model Selection Example: Regression Example: Regression Example: Regression Example: Regression Example: Regression Modern MDL! Five MDL Lectures Part I: Overview Codes Example 1: uniform code Code Length & Probability Code Lengths ‘are’ probabilities… …and probabilities ‘are’ code lengths! The Most Important Slide! The Most Important Slide! Example 1: uniform code/distr. Prefix codes distributions Prefix codes distributions General Recipe (Kraft) Prefix codes distributions Prefix codes distributions General Recipe (Kraft) Example 3: distributions codes Example 3: distributions codes The Most Important Slide! Remarks Part I: Overview Universal Codes Universal Codes Universal Codes Universal Codes Universal Codes Terminology Bayesian Mixtures are universal models Bayesian Mixtures are universal models 2-part MDL code is a universal model (code) Bayesian Mixtures are universal models 2-part MDL code is a universal model (code) 2-part vs. Bayes universal models Optimal Universal Model Optimal Universal Model - II MDL Model Selection MDL Model Selection

# Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.

Part 1 47:38
!NOW PLAYING

Part 2 44:43

Part 3 44:57

Part 4 46:51

# Description

We give a tutorial introduction to the *modern* Minimum Description Length (MDL) Principle, taking into account the many refinements and developments that have taken place in the 1990s. These do not seem to be widely known outside the information theory community. We will especially emphasize the use of MDL in classification. We also consider the connections between MDL, Bayesian inference, maximum entropy inference and structural risk minimization.