AI RESEARCH
Sharpness-Aware Machine Unlearning
arXiv CS.LG
•
ArXi:2506.13715v3 Announce Type: replace We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. While previous work prove that SAM improves generalization with noise memorization prevention, we show that SAM abandons such denoising property when fitting the forget set, leading to altered generalization depending on signal strength.