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)→

Original post →

More from Research

Research channel →