The two-user Gaussian interference channel: a deterministic view

TL;DR

This paper demonstrates that a deterministic model can effectively approximate the two-user Gaussian interference channel's capacity, simplifying analysis and providing insights, with a proven constant gap between the models.

Contribution

It introduces a deterministic channel model that approximates the Gaussian interference channel within a constant gap, simplifying capacity analysis.

Findings

Deterministic model approximates Gaussian channel capacity within a universal constant.

Capacity regions of deterministic and Gaussian channels differ by a constant.

Provides an alternative derivation of the constant gap capacity result.

Abstract

This paper explores the two-user Gaussian interference channel through the lens of a natural deterministic channel model. The main result is that the deterministic channel uniformly approximates the Gaussian channel, the capacity regions differing by a universal constant. The problem of finding the capacity of the Gaussian channel to within a constant error is therefore reduced to that of finding the capacity of the far simpler deterministic channel. Thus, the paper provides an alternative derivation of the recent constant gap capacity characterization of Etkin, Tse, and Wang. Additionally, the deterministic model gives significant insight towards the Gaussian channel.