2 papers
cs.LG2026
Towards Faithful Data Selection: Statistical Limits and Scalable Algorithms
Ahmed Mehdi Inane, Mahdi Haghifam, Gintare Karolina Dziugaite +1
What does it mean to have an optimal data selection algorithm? Optimality is conventionally framed as finding a subset that minimizes the population error of the classifier trained…
cs.LG2026
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite +1
Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model utility, particularly for large…