Computationally Efficient Feature Significance and Importance for Machine Learning Models

05/23/2019
by   Enguerrand Horel, et al.
0

We develop a simple and computationally efficient significance test for the features of a machine learning model. Our forward-selection approach applies to any model specification, learning task and variable type. The test is non-asymptotic, straightforward to implement, and does not require model refitting. It identifies the statistically significant features as well as feature interactions of any order in a hierarchical manner, and generates a model-free notion of feature importance. Numerical results illustrate its performance.

READ FULL TEXT

page 7

page 8

research
05/11/2021

Comparing interpretability and explainability for feature selection

A common approach for feature selection is to examine the variable impor...
research
05/28/2021

Generalized Permutation Framework for Testing Model Variable Significance

A common problem in machine learning is determining if a variable signif...
research
01/30/2021

Importance of feature engineering and database selection in a machine learning model: A case study on carbon crystal structures

Drive towards improved performance of machine learning models has led to...
research
10/27/2019

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

Feature importance estimates that inform users about the degree to which...
research
10/18/2019

Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification

Feature importance is commonly used to explain machine predictions. Whil...
research
06/19/2020

Exploring Weight Importance and Hessian Bias in Model Pruning

Model pruning is an essential procedure for building compact and computa...
research
11/03/2020

Multicollinearity Correction and Combined Feature Effect in Shapley Values

Model interpretability is one of the most intriguing problems in most of...

Please sign up or login with your details

Forgot password? Click here to reset