Visualizing Tree Decompositions

In order to do exact probabilistic inference on real life network efficiently, one must find a good Tree Decomposition of the network. This process is known as the Junction Tree algorithm. It's a bit hard to visualize the result, but while browsing tree decomposition graph pages on Wikipedia, I got an idea. Instead of bags with variables, we plot it as a collection of colored strips where each strip corresponds to a variable and Running Intersection property guarantees there will be no breaks.

Here's the result for the width-7 tree decomposition of the moralized Barley network



Mathematica source

Springer temporarily opens "Machine Learning" journal

Link here.
If you never heard of the journal "Machine Learning", it used to be number 1 ranked journal in ML, until board of editors resigned and founded the Journal of Machine Learning Research, possibly the greatest success story in open-access publishing

Prediction competitions

I just came across kaggle.com which is a platform for "s a platform for data prediction competitions." From brief glance, it seems the goal is to automate Netflix-prize-like competitions. It seems four competitions are currently active

SVM plots

Ulrich Bodenhofer has made some nifty SVM visualization code. One is Mathematica notebooks that takes libSVM model files and visualizes them, another one generates plots of Bayes optimal classifier on some synthetic 2d problems

Importance of naming things

Searching for "NIPS" in google blog-search mainly produces posts about nipples, my "CRF" subscription on delicious recently flooded me with links about "Chronic Renal Failure" (apparently a common feline ailment), and you can guess what I got when trying to find Bill Sutherlands "Beautiful Models" book (it's about statistical physics models).

Other unfortunate name choices -- hard-ass (hard as satisfiability, proposed for NP-complete problems before they had a name), Go programming language, hardcore model, Michael Jordan

As a rule of thumb, when coming up with a name for new technique, conference, concept, etc, it should satisfy at least one of two criteria:

• not already be a popular keyword in google
  
• be funny (ie RODEO ("regularization of derivative expectation operator") as an improvement on the LASSO (least absolute shrinkage and selection operator))