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)→
More from Research
- Diamandis: AI Cancer Navigator and $100 Genome Sequencing Close the Care Gap — PeterDiamandis · 2026-10-27
- EMNLP Oral: training-free Nexus Sampling cuts KV-cache memory 10x; OpenResearcher tops BrowseComp-Plus at 54.8% — yuz9yuz · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- Forking gap follows a power law in context frequency; masking rare n-grams shrinks it — ZimingLiu11 · 2026-10-27
- How forking happens: n-gram tables split logits into non-interacting subspaces — ZimingLiu11 · 2026-10-27
- The best LoRA explainer video yet: rank constraints meet intrinsic dimension — sophiamyang · 2026-10-27