Privately Counting Partially Ordered Data
Matthew Joseph, Mónica Ribero, Alexander Yu
2025年份
2顶会引用
摘要
We consider differentially private counting when each data point consists of d bits satisfying a partial order. Our main technical contribution is a problem-specific K-norm mechanism that runs in time O(d 2 ). Experiments show that, depending on the partial order in question, our solution dominates existing pure differentially private mechanisms, and can reduce their error by an order of magnitude or more.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Continual Release Moment Estimation with Differential PrivacyNikita P. Kalinin, Jalaj Upadhyay, Christoph H. LampertNeurIPS 2025 · 被引用 5 次
- Approximate Differential Privacy of the ℓ2 MechanismMatthew Joseph, Alex Kulesza, Alexander YuICML 2025
它引用的顶会 Paper3
- Private Query Release via the Johnson-Lindenstrauss TransformAleksandar NikolovSODA 2023 · 被引用 1 次
- Strong self-concordance and samplingAditi Laddha, Yin Tat Lee, Santosh S. VempalaSTOC 2020
- The power of factorization mechanisms in local and central differential privacyAlexander Edmonds, Aleksandar Nikolov, Jonathan R. UllmanSTOC 2020
相关 Paper
- A Joint Exponential Mechanism For Differentially Private Top-kJennifer Gillenwater, Matthew Joseph, Andres Muñoz Medina, Mónica Ribero DiazICML 2022 · 被引用 20 次
- Differentially Private Quantiles with Smaller ErrorJacob Imola, Fabrizio Boninsegna, Hannah Keller, Anders Aamand 等NeurIPS 2025 · 被引用 4 次
- Permute-and-Flip: A new mechanism for differentially private selectionRyan McKenna, Daniel SheldonNeurIPS 2020 · 被引用 66 次
- Differentially Private QuantilesJennifer Gillenwater, Matthew Joseph, Alex KuleszaICML 2021 · 被引用 2 次
- Counting Distinct Elements Under Person-Level Differential PrivacyThomas Steinke, Alexander KnopNeurIPS 2023 · 被引用 4 次
