Derives a federated van Trees lower bound under total clientwise sample-level zCDP for parameter estimation with squared l2 loss in federated learning protocols with arbitrary public-transcript interactions.
Optimal estimation in private distributed functional data analysis.arXiv preprint arXiv:2412.06582
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces FedHybrid and FedNewton for DP federated M-estimation, with finite-sample MSE bounds, minimax lower bound, and evaluations on vision datasets.
citing papers explorer
-
General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions
Derives a federated van Trees lower bound under total clientwise sample-level zCDP for parameter estimation with squared l2 loss in federated learning protocols with arbitrary public-transcript interactions.
-
Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
Introduces FedHybrid and FedNewton for DP federated M-estimation, with finite-sample MSE bounds, minimax lower bound, and evaluations on vision datasets.