PofoliaShared via Pofolia

Journal of the American Statistical Association· 2026Q1

Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints

Tommaso Cai, Abhinav Chakraborty, Lasse Vuursteen

Short summary

New federated learning estimators achieve minimax optimal convergence rates for nonparametric regression under heterogeneous distributed differential privacy (DP), handling varying sample sizes and privacy budgets across servers.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Artificial Intelligence

Artificial IntelligenceComputer Science