search

pwollstadt / IDTxl

The Information Dynamics Toolkit xl (IDTxl) is a comprehensive software package for efficient inference of networks and their node dynamics from multivariate time series data using information theory.
http://pwollstadt.github.io/IDTxl/
GNU General Public License v3.0
249 stars 76 forks source link

MI and CMI estimators add noise to the same data more than once #6

Closed pmediano closed 7 years ago

pmediano commented 7 years ago

Some MI and CMI estimators do in-place addition to add noise to the data (e.g. estimators_mi.py, line 89, var1 += np.random.normal(...)), which modifies the original variable. This is a problem because the estimator will keep adding more noise to the data if called multiple times.

pwollstadt commented 7 years ago

Fixed for JIDT estimators in commit 025a213def6bc02878c2904b170d26594487c56e. Also fixed in @pmediano's new OpenCL estimators (commits 4757d2bc21347bb4df2a9e3e2610ec718c9d9342 and c8a1b22911504dd3a21e3594cfa724bc26a1b9a2)