Author

Christopher Musco

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Differentially Private Synthetic Data from Sliced Chebyshev Moments

It is proved that, given a dataset of examples, SPLICE returns a private distribution with Sliced Wasserstein-1 distance $\tilde{O}(1/\sqrt{n})$ from the target, for constant privacy parameters, and a moment matching result of independent interest is proved.

Lucas Rosenblatt, R. Witter, Christopher Musco · 0 citations