ALU Theory: Quantifying Public-Private Data Mismatch on Unlearning
gkdziugaite · x · 2026-07-07
Unlike studies that assume perfect alignment between public and private data, this research explicitly models and analyzes the realistic scenario of distribution mismatch. It theoretically quantifies the impact of distribution shifts between public and private data sources on machine unlearning performance, making the framework much closer to real-world deployment scenarios.
Related event: ICML 2026 Paper Proposes ALU Framework for Large-Scale Machine Unlearning(5 posts)→
More from Research
- Datology webinar: Curation Studio matched top data baselines with under 20% compute — josh_wills · 2026-10-27
- KANLab: an interactive browser playground for Kolmogorov-Arnold Networks — Lukas Niehaus · 2026-10-27
- CMU's LLM2Cert synthesizes stability certificates verified via SMT and Lean — CarnegieMellonU · 2026-10-27
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- RSNA 2026 Deep Learning Labs return: eight hands-on AI classes over four days in Chicago — PRouzrokh · 2026-10-27
- Steering two orthogonal concept neurons makes a model compose "gnome" — Sauers_ · 2026-10-27