Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
We consider the problem of differentially private stochastic convex optimization (DP-SCO) in a distributed setting with clients, where each of them has a local dataset of i.i.d. data samples from an underlying data distribution. The objective is to design an algorithm to minimize a convex population loss using a collaborative effort across clients, while ensuring the privacy of the local datasets. In this work, we investigate the accuracy-communication-privacy trade-off for this problem. We establish matching converse and achievability results using a novel lower bound and a new algorithm for distributed DP-SCO based on Vaidya's plane cutting method. Thus, our results provide a complete characterization of the accuracy-communication-privacy trade-off for DP-SCO in the distributed setting.
View on arXiv