ITMLApr 20, 2018

Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder Learning

arXiv:1804.07675v275 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of characterizing communication limits in nonlinear fiber systems for researchers in optical communications, but it is incremental as it applies known autoencoder techniques to a specific domain.

The authors tackled the problem of computing achievable information rates for nonlinear fiber communication by using an end-to-end autoencoder to jointly optimize input and auxiliary distributions without explicit channel knowledge, resulting in a method that provides numerical AIR estimates for this simplified channel.

Machine learning is used to compute achievable information rates (AIRs) for a simplified fiber channel. The approach jointly optimizes the input distribution (constellation shaping) and the auxiliary channel distribution to compute AIRs without explicit channel knowledge in an end-to-end fashion.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes