The paper gives a single-letter characterization of optimal rates for remote channel synthesis and proves that direct per-symbol synthesis is strictly suboptimal at low common randomness.
DP-REC: Private & Communication-Efficient Federated Learning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Privacy and communication efficiency are important challenges in federated training of neural networks, and combining them is still an open problem. In this work, we develop a method that unifies highly compressed communication and differential privacy (DP). We introduce a compression technique based on Relative Entropy Coding (REC) to the federated setting. With a minor modification to REC, we obtain a provably differentially private learning algorithm, DP-REC, and show how to compute its privacy guarantees. Our experiments demonstrate that DP-REC drastically reduces communication costs while providing privacy guarantees comparable to the state-of-the-art.
citation-role summary
citation-polarity summary
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Remote Channel Synthesis
The paper gives a single-letter characterization of optimal rates for remote channel synthesis and proves that direct per-symbol synthesis is strictly suboptimal at low common randomness.