← Search

Mikaël Monet

2 accepted papers

2021

The Tractability of SHAP-Score-Based Explanations for Classification over Deterministic and Decomposable Boolean Circuits

AAAI 2021technical

Scores based on Shapley values are widely used for providing explanations to classification results over machine learning models. A prime example of this is the influential SHAP-score, a version of the Shapley value that can help explain the result of a learned model on a specific entity by assignin…

Cited by 53Source ↗PDF ↗Scholar ↗
2020

Model Interpretability through the lens of Computational Complexity

NeurIPS 2020poster

In spite of several claims stating that some models are more interpretable than others --e.g., "linear models are more interpretable than deep neural networks"-- we still lack a principled notion of interpretability that allows us to formally compare among different classes of models. We make a step…

Cited by 128Source ↗PDF ↗Scholar ↗