##Optimal Two Step Prediction: Adaptive Validation
This code is associated with the article:
"Optimal two-step prediction in regression" by Didier Chételat, Johannes Lederer, Joseph Salmon
The correpsonding paper is available on ArXiV at http://arxiv.org/abs/1410.5014
The Demo_AVP.py provides an exemple of the Adaptive Validation on two cases:
-
the Lasso
-
the Thresholded Ridge Regression
##Dependencies AVp is tested to work under Python 2.7.
The required dependencies to build the software are NumPy >= 1.6.2, SciPy >= 0.9 and a working C/C++ compiler, and of course scikit-learn > 0.15
For running the examples Seaborn>= 0.4.0 is required.