ALU Framework: Public Data Injection Reduces Unlearning Cost to O(1/n^2)

gkdziugaite · x · 2026-07-07

The research team proposed the Asymmetric Langevin Unlearning (ALU) framework, with the core idea of utilizing public data to reduce the privacy cost of machine unlearning. Mathematical proofs show that public data injection can boost the suppression factor for unlearning costs to O(1/npub^2), providing theoretical guarantees for solving large-scale certified unlearning problems.

Related event: ICML 2026 Paper Proposes ALU Framework for Large-Scale Machine Unlearning(5 posts)→

Original post →

More from Research

Research channel →