English

Minimax Bounds for Distributed Logistic Regression

Information Theory 2019-10-04 v1 math.IT Statistics Theory Statistics Theory

Abstract

We consider a distributed logistic regression problem where labeled data pairs (Xi,Yi)Rd×{1,1}(X_i,Y_i)\in \mathbb{R}^d\times\{-1,1\} for i=1,,ni=1,\ldots,n are distributed across multiple machines in a network and must be communicated to a centralized estimator using at most kk bits per labeled pair. We assume that the data XiX_i come independently from some distribution PXP_X, and that the distribution of YiY_i conditioned on XiX_i follows a logistic model with some parameter θRd\theta\in\mathbb{R}^d. By using a Fisher information argument, we give minimax lower bounds for estimating θ\theta under different assumptions on the tail of the distribution PXP_X. We consider both 2\ell^2 and logistic losses, and show that for the logistic loss our sub-Gaussian lower bound is order-optimal and cannot be improved.

Keywords

Cite

@article{arxiv.1910.01625,
  title  = {Minimax Bounds for Distributed Logistic Regression},
  author = {Leighton Pate Barnes and Ayfer Ozgur},
  journal= {arXiv preprint arXiv:1910.01625},
  year   = {2019}
}
R2 v1 2026-06-23T11:34:01.867Z