Iterative subtraction method for Feature Ranking
This addresses feature selection for physicists analyzing specific particle physics data, but it is incremental as it compares existing methods rather than introducing a new one.
The paper tackled the problem of ranking highly correlated features for classifying top-quark pair production with Higgs boson decay at the LHC, finding that the Iterative Removal method outperformed other ranking techniques.
Training features used to analyse physical processes are often highly correlated and determining which ones are most important for the classification is a non-trivial tasks. For the use case of a search for a top-quark pair produced in association with a Higgs boson decaying to bottom-quarks at the LHC, we compare feature ranking methods for a classification BDT. Ranking methods, such as the BDT Selection Frequency commonly used in High Energy Physics and the Permutational Performance, are compared with the computationally expense Iterative Addition and Iterative Removal procedures, while the latter was found to be the most performant.