Zhiqi Bu

Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger

2022 · arXiv (Cornell University)

Per-example gradient clipping is a key algorithmic step that enables practical differential private (DP) training for deep learning models. The choice of clipping threshold R, however, is vital for achieving high accuracy under DP. We …

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

2024 · arXiv (Cornell University)

Machine unlearning has been used to remove unwanted knowledge acquired by large language models (LLMs). In this paper, we examine machine unlearning from an optimization perspective, framing it as a regularized multi-task optimization problem, where …