2025
A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
NeurIPS 2025poster
We study the problem of differentially private second moment estimation and present a new algorithm that achieve strong privacy-utility trade-offs even for worst-case inputs under subsamplability assumptions on the data. We call an input $(m,\alpha,\beta)$-subsamplable if a random subsample of size…