← Search

Ahmad Chamma

2 accepted papers

2024

Variable Importance in High-Dimensional Settings Requires Grouping

AAAI 2024technical

Explaining the decision process of machine learning algorithms is nowadays crucial for both model’s performance enhancement and human comprehension. This can be achieved by assessing the variable importance of single variables, even for high-capacity non-linear methods, e.g. Deep Neural Networks (DN…

2023

Statistically Valid Variable Importance Assessment through Conditional Permutations

NeurIPS 2023poster

Variable importance assessment has become a crucial step in machine-learning applications when using complex learners, such as deep neural networks, on large-scale data. Removal-based importance assessment is currently the reference approach, particularly when statistical guarantees are sought to ju…

Cited by 16SourcePDFScholar