Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910422935797760 |
|---|---|
| author | Zhang, Zhe Nakada, Ryumei Zhang, Linjun |
| author_facet | Zhang, Zhe Nakada, Ryumei Zhang, Linjun |
| contents | Differentially private federated learning is crucial for maintaining privacy in distributed environments. This paper investigates the challenges of high-dimensional estimation and inference under the constraints of differential privacy. First, we study scenarios involving an untrusted central server, demonstrating the inherent difficulties of accurate estimation in high-dimensional problems. Our findings indicate that the tight minimax rates depends on the high-dimensionality of the data even with sparsity assumptions. Second, we consider a scenario with a trusted central server and introduce a novel federated estimation algorithm tailored for linear regression models. This algorithm effectively handles the slight variations among models distributed across different machines. We also propose methods for statistical inference, including coordinate-wise confidence intervals for individual parameters and strategies for simultaneous inference. Extensive simulation experiments support our theoretical advances, underscoring the efficacy and reliability of our approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16287 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference Zhang, Zhe Nakada, Ryumei Zhang, Linjun Machine Learning Cryptography and Security Statistics Theory Methodology Differentially private federated learning is crucial for maintaining privacy in distributed environments. This paper investigates the challenges of high-dimensional estimation and inference under the constraints of differential privacy. First, we study scenarios involving an untrusted central server, demonstrating the inherent difficulties of accurate estimation in high-dimensional problems. Our findings indicate that the tight minimax rates depends on the high-dimensionality of the data even with sparsity assumptions. Second, we consider a scenario with a trusted central server and introduce a novel federated estimation algorithm tailored for linear regression models. This algorithm effectively handles the slight variations among models distributed across different machines. We also propose methods for statistical inference, including coordinate-wise confidence intervals for individual parameters and strategies for simultaneous inference. Extensive simulation experiments support our theoretical advances, underscoring the efficacy and reliability of our approaches. |
| title | Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference |
| topic | Machine Learning Cryptography and Security Statistics Theory Methodology |
| url | https://arxiv.org/abs/2404.16287 |