Search Results for author:
Found 2 papers, 0 papers with code
Continual Mean Estimation Under User-Level Privacy
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 $\tilde{O}(1/\sqrt{t}+\sqrt{M}_t/t\varepsilon)$.
Multiple Support Recovery Using Very Few Measurements Per Sample
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
