Asymmetric Langevin Unlearning uses public data to suppress unlearning noise costs by O(1/n_pub²), enabling practical mass unlearning with preserved utility under distribution mismatch.
Remember
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Second-order optimizers retain residual geometric memory in their state after unlearning that first-order metrics miss, and only controlled eigendecay perturbations fully erase it.
Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
citing papers explorer
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
Asymmetric Langevin Unlearning uses public data to suppress unlearning noise costs by O(1/n_pub²), enabling practical mass unlearning with preserved utility under distribution mismatch.
-
Shape of Memory: a Geometric Analysis of Machine Unlearning in Second-Order Optimizers
Second-order optimizers retain residual geometric memory in their state after unlearning that first-order metrics miss, and only controlled eigendecay perturbations fully erase it.
-
Form and Function: Machine Unlearning as a Problem of Misaligned States
Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.