Minimax Bounds for Distributed Logistic Regression

Abstract
We consider a distributed logistic regression problem where labeled data pairs for are distributed across multiple machines in a network and must be communicated to a centralized estimator using at most bits per labeled pair. We assume that the data come independently from some distribution , and that the distribution of conditioned on follows a logistic model with some parameter . By using a Fisher information argument, we give minimax lower bounds for estimating under different assumptions on the tail of the distribution . We consider both and logistic losses, and show that for the logistic loss our sub-Gaussian lower bound is order-optimal and cannot be improved.
View on arXivComments on this paper