Summary of Federated Online Prediction From Experts with Differential Privacy: Separations and Regret Speed-ups, by Fengyu Gao et al.
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
by Fengyu Gao, Ruiquan Huang, Jing Yang
First submitted to arxiv on: 27 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (stat.ML)
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 The paper investigates the challenges of privately sharing expert predictions in a federated learning framework, where multiple clients collaborate to minimize regret while ensuring differential privacy. The authors propose novel algorithms, Fed-DP-OPE-Stoch and Fed-SVT, that achieve significant speed-ups in average regret compared to single-player counterparts, under both pure and approximate differential privacy constraints. The results also establish lower bounds for oblivious adversaries, demonstrating the importance of collaboration among clients. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how experts can share their predictions with others privately while working together to make better decisions. It shows that by sharing information in a special way, experts can make faster and more accurate decisions than if they worked alone. The authors also found limits on what can be achieved when working together against an unknown adversary. |
Keywords
» Artificial intelligence » Federated learning
