Simple tutorial implementing a gaussian information bottleneck based on the great paper from Gal Chechik, Amir Globerson, Naftali Tishby, and Yair Weiss (JMLR 2005).
Starting from a joint Gaussian (X,Y), the problem is to find a linear projection A that compresses a variable X while preserving as much information as possible about Y.
The tradeoff between compression and preservation is given by a parameter
-
Notifications
You must be signed in to change notification settings - Fork 0
Simple tutorial implementing a gaussian information bottleneck
License
michnard/GIB_tutorial
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Simple tutorial implementing a gaussian information bottleneck
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published