Abstract
We present an asymptotically optimal (ε, δ) differentially private mechanism for answering multiple, adaptively asked, ∆-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a significant advantage that it adds independent bounded noise to each query, thus providing an absolute error bound. Additionally, we apply our algorithm in adaptive data analysis, obtaining an improved guarantee for answering multiple queries regarding some underlying distribution using a finite sample. Numerical computations show that the bounded-noise mechanism outperforms the Gaussian mechanism in many standard settings.
| Original language | English |
|---|---|
| Pages (from-to) | 625-661 |
| Number of pages | 37 |
| Journal | Proceedings of Machine Learning Research |
| Volume | 178 |
| State | Published - 2022 |
| Externally published | Yes |
| Event | 35th Conference on Learning Theory, COLT 2022 - London, United Kingdom Duration: 2 Jul 2022 → 5 Jul 2022 https://proceedings.mlr.press/v178 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability