
The proposed advanced adaptive additive (AAA) mechanism is a distribution-aware approach that addresses the average utility and tackles the classical mean estimation problem under local differential privacy constraints.


coremsg

adaptive-mechanism-for-locally-differential-private-mean-estimation


Adaptive Mechanism for Locally Differential Private Mean Estimation


title_rewrite


By adding independent but non-identically distributed (i.n.i.d.) noise across the coordinates of a multi-dimensional query response, the proposed mechanisms can achieve higher accuracy than the conventional independent and identically distributed (i.i.d.) noise addition, while still satisfying the given differential privacy constraints.


exploiting-coordinate-wise-disparity-to-achieve-higher-utility-in-differentially-private-mechanisms


Exploiting Coordinate-wise Disparity to Achieve Higher Utility in Differentially Private Mechanisms
