NeurIPS 2023: DP Papers

Benutzer

what are the papers discussing differential privacy ?

Chat NeurIPS

The search for papers discussing differential privacy at NeurIPS 2023 yielded a variety of results. Here's a summary of some notable papers in this area:

Synthcity: A Benchmark Framework for Diverse Use Cases of Tabular Synthetic Data
- Authors: Zhaozhi Qian, Rob Davis, Mihaela van der Schaar
- Abstract: This paper introduces Synthcity, an open-source Python library for benchmarking synthetic data generators. It discusses differential privacy in the context of diverse data modalities and use cases, including privacy preservation.
- Relevant Page: 11
- Link to Paper
Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy
- Authors: Bonwoo Lee, Jeongyoun Ahn, Cheolwoo Park
- Relevant Pages: 1, 2
- Link to Paper
Counting Distinct Elements Under Person-Level Differential Privacy
- Authors: Thomas Steinke, Alexander Knop
- Abstract: This study addresses the challenge of counting the number of distinct elements in a dataset under the constraint of person-level differential privacy.
- Relevant Page: 1
- Link to Paper
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
- Authors: Zhiqin Yang, Yonggang Zhang, Yu Zheng, Xinmei Tian, Hao Peng, Tongliang Liu, Bo Han
- Abstract: FedFed, a novel approach in federated learning to address data heterogeneity, discusses differential privacy as a framework for data privacy.
- Relevant Page: 3
- Link to Paper
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy
- Authors: Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie Su
- Relevant Page: 11
- Link to Paper
Dynamic Personalized Federated Learning with Adaptive Differential Privacy
- Authors: Xiyuan Yang, Wenke Huang, Mang Ye
- Abstract: This paper proposes a federated learning method with dynamic personalization and adaptive differential privacy.
- Relevant Pages: 4, 5
- Link to Paper
Training Private Models That Know What They Don’t Know
- Authors: Stephan Rabanser, Anvith Thudi, Abhradeep Guha Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot
- Abstract: The paper investigates selective classifiers under differential privacy constraints and proposes a novel evaluation mechanism.
- Relevant Pages: 11, 2, 3
- Link to Paper
Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency
- Authors: Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Suggala
- Relevant Pages: 14, 10, 11
- Link to Paper
Adaptive Privacy Composition for Accuracy-first Mechanisms
- Authors: Ryan Rogers, Gennady Samorodnitsk, Steven Wu, Aaditya Ramdas
- Relevant Page: 1
- Link to Paper
The Target-Charging Technique for Privacy Analysis across Interactive Computations
- Authors: Edith Cohen, Xin Lyu
- Relevant Page: 11
- Link to Paper

These papers cover a range of topics related to differential privacy, including synthetic data generation, federated learning, and privacy-preserving algorithms in machine learning.

The search for papers discussing differential privacy at NeurIPS 2023 yielded a variety of results. Here's a summary of some notable papers in this area: 1. **Synthcity: A Benchmark Framework for Diverse Use Cases of Tabular Synthetic Data** - **Authors:** Zhaozhi Qian, Rob Davis, Mihaela van der Schaar - **Abstract:** This paper introduces Synthcity, an open-source Python library for benchmarking synthetic data generators. It discusses differential privacy in the context of diverse data modalities and use cases, including privacy preservation. - **Relevant Page:** 11 - [Link to Paper](https://openreview.net/pdf?id=uIppiU2JKP#page=11) 2. **Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy** - **Authors:** Bonwoo Lee, Jeongyoun Ahn, Cheolwoo Park - **Relevant Pages:** 1, 2 - [Link to Paper](https://openreview.net/pdf?id=XzTM9gVRT4#page=1) 3. **Counting Distinct Elements Under Person-Level Differential Privacy** - **Authors:** Thomas Steinke, Alexander Knop - **Abstract:** This study addresses the challenge of counting the number of distinct elements in a dataset under the constraint of person-level differential privacy. - **Relevant Page:** 1 - [Link to Paper](https://openreview.net/pdf?id=zdli6OxpWd#page=1) 4. **FedFed: Feature Distillation against Data Heterogeneity in Federated Learning** - **Authors:** Zhiqin Yang, Yonggang Zhang, Yu Zheng, Xinmei Tian, Hao Peng, Tongliang Liu, Bo Han - **Abstract:** FedFed, a novel approach in federated learning to address data heterogeneity, discusses differential privacy as a framework for data privacy. - **Relevant Page:** 3 - [Link to Paper](https://openreview.net/pdf?id=phnGilhPH8#page=3) 5. **Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy** - **Authors:** Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie Su - **Relevant Page:** 11 - [Link to Paper](https://openreview.net/pdf?id=pw5hEuEroL#page=11) 6. **Dynamic Personalized Federated Learning with Adaptive Differential Privacy** - **Authors:** Xiyuan Yang, Wenke Huang, Mang Ye - **Abstract:** This paper proposes a federated learning method with dynamic personalization and adaptive differential privacy. - **Relevant Pages:** 4, 5 - [Link to Paper](https://openreview.net/pdf?id=RteNLuc8D9#page=4) 7. **Training Private Models That Know What They Don’t Know** - **Authors:** Stephan Rabanser, Anvith Thudi, Abhradeep Guha Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot - **Abstract:** The paper investigates selective classifiers under differential privacy constraints and proposes a novel evaluation mechanism. - **Relevant Pages:** 11, 2, 3 - [Link to Paper](https://openreview.net/pdf?id=EgCjf1vjMB#page=11) 8. **Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency** - **Authors:** Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Suggala - **Relevant Pages:** 14, 10, 11 - [Link to Paper](https://openreview.net/pdf?id=N6FhEMnxCU#page=14) 9. **Adaptive Privacy Composition for Accuracy-first Mechanisms** - **Authors:** Ryan Rogers, Gennady Samorodnitsk, Steven Wu, Aaditya Ramdas - **Relevant Page:** 1 - [Link to Paper](https://openreview.net/pdf?id=QezJbfW01r#page=1) 10. **The Target-Charging Technique for Privacy Analysis across Interactive Computations** - **Authors:** Edith Cohen, Xin Lyu - **Relevant Page:** 11 - [Link to Paper](https://openreview.net/pdf?id=7yjsYrajlt#page=11) These papers cover a range of topics related to differential privacy, including synthetic data generation, federated learning, and privacy-preserving algorithms in machine learning.