Noisy fine-tuning with gradient or model clipping on retained data provably removes the influence of forget data, with guarantees that need no smoothness or convexity assumptions.
Contraction of E _ -divergence and its applications to privacy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Certified Unlearning for Neural Networks
Noisy fine-tuning with gradient or model clipping on retained data provably removes the influence of forget data, with guarantees that need no smoothness or convexity assumptions.