Preprint
Aug 2026
Interpretable AI with Local Distillation
Local distillation is proposed, in which a black-box teacher guides a regularized linear"student" model at each query point, and it is proved that this randomization yields feature-selection probabilities that are stable under small perturbations of the training responses.
Erin Craig, Yiling Huang, Snigdha Panigrahi
· 0 citations