Optimal Compression of Unit Norm Vectors in the High Distortion Regime

TL;DR

This paper investigates the optimal compression of unit norm vectors in high-distortion regimes for distributed learning, showing simple schemes are nearly optimal in worst-case scenarios with randomized methods.

Contribution

It provides a comprehensive analysis of the minimal bits needed to compress vectors with acceptable distortion, focusing on worst-case, high-distortion settings, and compares biased and unbiased methods.

Findings

Simple compression schemes are nearly optimal.

Optimal rates depend on the distortion level and vector properties.

Results unify and extend existing knowledge in high-distortion vector compression.

Abstract

Motivated by the need for communication-efficient distributed learning, we investigate the method for compressing a unit norm vector into the minimum number of bits, while still allowing for some acceptable level of distortion in recovery. This problem has been explored in the rate-distortion/covering code literature, but our focus is exclusively on the "high-distortion" regime. We approach this problem in a worst-case scenario, without any prior information on the vector, but allowing for the use of randomized compression maps. Our study considers both biased and unbiased compression methods and determines the optimal compression rates. It turns out that simple compression schemes are nearly optimal in this scenario. While the results are a mix of new and known, they are compiled in this paper for completeness.