Regression with Label Differential Privacy

Autor:	Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Leeman, Ethan, Manurangsi, Pasin, Varadarajan, Avinash V, Zhang, Chiyuan
Rok vydání:	2022
Předmět:	Computer Science - Machine Learning Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	We study the task of training regression models with the guarantee of label differential privacy (DP). Based on a global prior distribution on label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a "randomized response on bins", and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm. Comment: Appeared at ICLR '23, 28 pages, 6 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.06074 Zobrazit plný text záznamu View this record from Arxiv