Preprint
Oct 2026
Efficient Exact Unlearning for Federated Zeroth-Order Optimization
Two stable zeroth-order learning algorithms are designed and proved exact unlearning for both algorithms: the model and saved state have the same joint distribution as retraining with the corresponding learner on retained data.
Wei-Jun Yin, Yan-Qing Yao, Falko Dressler et al.
· 0 citations