
Counterfactual explanations must be robust to algorithmic uncertainty in randomized ensembles.


coremsg

don-t-explain-noise-robust-counterfactuals-for-randomized-ensembles


Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles


title_rewrite


This work proposes a novel interval abstraction technique that provides deterministic robustness guarantees for counterfactual explanations under plausible model changes.


provably-robust-counterfactual-explanations-for-parametric-machine-learning-models


Provably Robust Counterfactual Explanations for Parametric Machine Learning Models
