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.
and Chewi, Sinho , month = dec, year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
New RSLMC sampling algorithms achieve uniform-in-time W2 error bounds of order O(sqrt(d) h) under gradient Lipschitz and log-Sobolev assumptions, with modified versions for superlinear gradient growth and supporting numerical examples.
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.
-
When Langevin Monte Carlo Meets Randomization: New Sampling Algorithms with Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness
New RSLMC sampling algorithms achieve uniform-in-time W2 error bounds of order O(sqrt(d) h) under gradient Lipschitz and log-Sobolev assumptions, with modified versions for superlinear gradient growth and supporting numerical examples.