no code implementations • 20 Dec 2022 • Anand Jerry George, Lekshmi Ramesh, Aditya Vikram Singh, Himanshu Tyagi
We provide an algorithm that outputs a mean estimate at every time instant $t$ such that the overall release is user-level $\varepsilon$-DP and has the following error guarantee: Denoting by $M_t$ the maximum number of samples contributed by a user, as long as $\tilde{\Omega}(1/\varepsilon)$ users have $M_t/2$ samples each, the error at time $t$ is $\tilde{O}(1/\sqrt{t}+\sqrt{M}_t/t\varepsilon)$.
no code implementations • 20 May 2021 • Lekshmi Ramesh, Chandra R. Murthy, Himanshu Tyagi
For a given budget of $m$ measurements per sample, the goal is to recover the $\ell$ underlying supports, in the absence of the knowledge of group labels.