Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning
For machine learning practitioners requiring verifiable unlearning, this provides a principled framework with theoretical guarantees, though it is an incremental step in the unlearning paradigm.
This paper links machine unlearning to data distribution structure, showing that precise distribution inference enables exact unlearning signals. The method achieves the closest classifier to the ideal retrained model across three forgetting scenarios.
This paper proposes a paradigm shift linking machine unlearning directly to the structure of the data distributions rather than a mere update of the neural network parameters. We show that inferring these distributions with precision enables distilling the exact unlearning signal induced by the modeling. Theoretical bounds on the Kullback-Leibler divergence from the ideal retrained model to our unlearned model, under verifiable admissibility criterion, reveal the soundness of our framework. This method is experimentally validated over three forgetting scenarios as reaching the closest classifier to the ideal retrained model when compared to competitors.