Algorithmically Effective Differentially Private Synthetic Data

February 11, 2023 Β· Declared Dead Β· πŸ› Annual Conference Computational Learning Theory

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yiyun He, Roman Vershynin, Yizhe Zhu arXiv ID 2302.05552 Category cs.DS: Data Structures & Algorithms Cross-listed cs.CR, math.PR, math.ST Citations 12 Venue Annual Conference Computational Learning Theory Last Checked 4 months ago
Abstract
We present a highly effective algorithmic approach for generating $\varepsilon$-differentially private synthetic data in a bounded metric space with near-optimal utility guarantees under the 1-Wasserstein distance. In particular, for a dataset $X$ in the hypercube $[0,1]^d$, our algorithm generates synthetic dataset $Y$ such that the expected 1-Wasserstein distance between the empirical measure of $X$ and $Y$ is $O((\varepsilon n)^{-1/d})$ for $d\geq 2$, and is $O(\log^2(\varepsilon n)(\varepsilon n)^{-1})$ for $d=1$. The accuracy guarantee is optimal up to a constant factor for $d\geq 2$, and up to a logarithmic factor for $d=1$. Our algorithm has a fast running time of $O(\varepsilon dn)$ for all $d\geq 1$ and demonstrates improved accuracy compared to the method in (Boedihardjo et al., 2022) for $d\geq 2$.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Data Structures & Algorithms

Died the same way β€” πŸ‘» Ghosted