Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression

Abstract

We study the statistical complexity of private linear regression under an unknown, potentially ill-conditioned covariate distribution. Somewhat surprisingly, under privacy constraints the intrinsic complexity is \emph{not} captured by the usual covariance matrix but rather its $L_1$ analogues. Building on this insight, we establish minimax convergence rates for both the central and local privacy models and introduce an Information-Weighted Regression method that attains the optimal rates. As application, in private linear contextual bandits, we propose an efficient algorithm that achieves rate-optimal regret bounds of order $\sqrt{T}+\frac{1}{\alpha}$ and $\sqrt{T}/\alpha$ under joint and local $\alpha$-privacy models, respectively. Notably, our results demonstrate that joint privacy comes at almost no additional cost, addressing the open problems posed by Azize and Basu (2024).