Geometric Lower Bounds for Distributed Parameter Estimation under Communication Constraints

TL;DR

This paper establishes fundamental lower bounds on the accuracy of distributed parameter estimation under communication constraints, revealing how limited communication reduces effective sample size and varies with model structure.

Contribution

It introduces a geometric approach to derive lower bounds that bypasses strong data processing inequalities, generalizing and simplifying previous results.

Findings

Communication constraints reduce effective sample size by a factor of d for small k.

The sample size penalty diminishes exponentially with increasing k in some models.

In models with sub-Gaussian structure, the reduction is only linear with k.

Abstract

We consider parameter estimation in distributed networks, where each sensor in the network observes an independent sample from an underlying distribution and has $k$ bits to communicate its sample to a centralized processor which computes an estimate of a desired parameter. We develop lower bounds for the minimax risk of estimating the underlying parameter for a large class of losses and distributions. Our results show that under mild regularity conditions, the communication constraint reduces the effective sample size by a factor of $d$ when $k$ is small, where $d$ is the dimension of the estimated parameter. Furthermore, this penalty reduces at most exponentially with increasing $k$, which is the case for some models, e.g., estimating high-dimensional distributions. For other models however, we show that the sample size reduction is re-mediated only linearly with increasing $k$, e.g. when some sub-Gaussian structure is available. We apply our results to the distributed setting with product Bernoulli model, multinomial model, Gaussian location models, and logistic regression which recover or strengthen existing results. Our approach significantly deviates from existing approaches for developing information-theoretic lower bounds for communication-efficient estimation. We circumvent the need for strong data processing inequalities used in prior work and develop a geometric approach which builds on a new representation of the communication constraint. This approach allows us to strengthen and generalize existing results with simpler and more transparent proofs.