提出更精确的无线联邦学习隐私与收敛分析，解决传统方法的局限性。
When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
- 考虑设备选择和小批量采样，改进隐私损失建模。
- 证明隐私损失随迭代次数趋于稳定而非发散。
- 给出带梯度裁剪的收敛保证，揭示隐私与性能权衡。
差分隐私无线联邦学习（DPWFL）是一种保护用户敏感数据的有前景框架。然而，如何精确刻画隐私损失仍是未解问题，现有研究还受限于依赖严格凸性假设或忽略梯度裁剪影响的收敛分析。为此，本文针对一般光滑非凸损失目标，对DPWFL的隐私与收敛进行了综合分析。分析中显式包含设备选择和小批量采样，证明隐私损失可随迭代次数收敛至常数而非发散。此外，我们建立了包含梯度裁剪的收敛保证，并推导出明确的隐私-效用权衡关系。数值结果验证了理论结论。
原文摘要 · Abstract (English)
Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize privacy loss remain open, and existing work is further limited by convergence analyses that rely on restrictive convexity assumptions or ignore the effect of gradient clipping. To overcome these issues, we present a comprehensive analysis of privacy and convergence for DPWFL with general smooth non-convex loss objectives. Our analysis explicitly incorporates both device selection and mini-batch sampling, and shows that the privacy loss can converge to a constant rather than diverge with the number of iterations. Moreover, we establish convergence guarantees with gradient clipping and derive an explicit privacy-utility trade-off. Numerical results validate our theoretical findings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。