Differentially Private Linear Regression over Fully Decentralized Datasets
This work addresses privacy-preserving machine learning for decentralized data settings, offering a method with theoretical guarantees, though it appears incremental as it builds on existing differential privacy and decentralized optimization techniques.
The paper tackles the problem of performing differentially private linear regression on fully decentralized datasets, presenting an algorithm with a theoretically derived privacy budget and bounded solution error that scales as O(t) for O(1/t) step size and O(exp(t^{1-e})) for O(t^{-e}) step size.
This paper presents a differentially private algorithm for linear regression learning in a decentralized fashion. Under this algorithm, privacy budget is theoretically derived, in addition to that the solution error is shown to be bounded by $O(t)$ for $O(1/t)$ descent step size and $O(\exp(t^{1-e}))$ for $O(t^{-e})$ descent step size.