Summary of Differentially Private Online Federated Learning with Correlated Noise, by Jiaojiao Zhang and Linglingzhi Zhu and Mikael Johansson
Differentially Private Online Federated Learning with Correlated Noise
by Jiaojiao Zhang, Linglingzhi Zhu, Mikael Johansson
First submitted to arxiv on: 25 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This novel algorithm for online federated learning uses temporally correlated noise to balance utility with privacy while releasing models continuously. The perturbed iterate analysis helps control the impact of DP noise on utility, addressing challenges posed by non-iid data and local updates. By controlling drift errors under quasi-strong convexity conditions, the algorithm establishes a dynamic regret bound over the entire time horizon, considering key parameters and environmental changes. Numerical experiments demonstrate its effectiveness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops an innovative way to keep models private while sharing them online. It creates a special kind of noise that helps maintain both privacy and usefulness. The method handles noisy data and updates from different sources. By understanding how this algorithm works, we can see why it’s important for ensuring privacy in complex environments. |
Keywords
* Artificial intelligence * Federated learning
