Jump to Content

Leveraging Bias-Variance Trade-offs for Regression with Label Differential Privacy

Avinash Varadarajan
Chiyuan Zhang
Ethan Leeman
Pritish Kamath
NeurIPS 2023 (2023)


We propose a new family of label randomization mechanisms for the task of training regression models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better noising mechanisms depending on a privately estimated prior distribution over the labels. We demonstrate that these mechanisms achieve state-of-the-art privacy-accuracy trade-offs on several datasets, highlighting the importance of bias-reducing constraints when training neural networks with label DP. We also provide theoretical results shedding light on the structural properties of the optimal bias-reduced mechanisms.