Story
arxiv_cs_lg · Sep 8, 2026 · paper
Source brief
The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
arxiv.orgSep 8, 2026
original source linked
In brief
Approximate machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. We identify a previously undocumented confound in how unlearning is evaluated...
Feed lens
evaluation