Dec 7, 2021 · Our algorithms arise from a new framework that provides a general blueprint for modifying convex relaxations for robust estimation to satisfy ...
Abstract. We give the first polynomial time and sample (ε, δ)-differentially private (DP) algorithm to esti- mate the mean, covariance and higher moments in ...
Dec 7, 2021 · Our algorithm succeeds for families of distributions that satisfy two well-studied properties in prior works on robust estimation: certifiable ...
Dec 6, 2021 · In this work, we consider the problem of efficiently estimating the mean, covariance and, more generally, the higher moments of an unknown high- ...
Dec 15, 2022 · Our approximate DP algorithms are based on a substantial upgrade of the method of stabilizing convex relaxations introduced in [Kothari et al., ...
People also ask
What is a robust estimation method?
What is doubly robust estimation?
Private robust estimation by stabilizing convex relaxations. P Kothari, P Manurangsi, A Velingker. Conference on Learning Theory, 723-777, 2022. 52, 2022. 系统 ...
Private Robust Estimation by Stabilizing Convex Relaxations With Pasin Manurangsi and Ameya Velingker. COLT, 2022; List-decodable Covariance Estimation With ...
We prove a new lower bound on differentially private covariance estimation to show that the dependence on the condition number κ in the above sample bound is ...
Private Robust Estimation by Stabilizing Convex Relaxations. In Proceedings of the 35th Annual Conference on Learning Theory (COLT '22). 723–777. https ...
In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) with heavy-tailed data, where the ...