AI RESEARCH

Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms

arXiv CS.LG

ArXi:2603.26227v1 Announce Type: cross We study privacy-preserving sparse linear regression in the high-dimensional regime, focusing on the LASSO estimator. We analyze two widely used mechanisms for differential privacy: output perturbation, which injects noise into the estimator, and objective perturbation, which adds a random linear term to the loss function. Using approximate message passing (AMP), we characterize the typical behavior of these estimators under random design and privacy noise.