End-to-End Learning for VCSEL-Based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities

Optical interconnects (OIs) based on vertical-cavity surface-emitting lasers (VCSELs) are the main workhorse within data centers, supercomputers, and even vehicles, providing low-cost, high-rate connectivity. VCSELs must operate under extremely harsh and time-varying conditions, thus requiring adaptive and flexible designs of the communication chain. Such designs can be built based on mathematical models (model-based design) or learned from data (machine learning (ML) based design). Various ML techniques have recently come to the forefront, replacing individual components in the transmitters and receivers with deep neural networks. Beyond such component-wise learning, end-to-end (E2E) autoencoder approaches can reach the ultimate performance through co-optimizing entire parameterized transmitters and receivers. This tutorial paper aims to provide an overview of ML for VCSEL-based OIs, with a focus on E2E approaches, dealing specifically with the unique challenges facing VCSELs, such as the wide temperature variations and complex models.

Automated summary

Optical interconnects (OIs) based on vertical-cavity surface-emitting lasers (VCSELs) are widely used in data centers, supercomputers, and vehicles for low-cost, high-rate connectivity. Machine learning (ML) techniques, including deep neural networks, have been applied to improve the performance of VCSEL-based OIs. End-to-end (E2E) autoencoder approaches can optimize the entire parameterized transmitters and receivers for ultimate performance. This tutorial paper provides an overview of ML for VCSEL-based OIs, focusing on E2E approaches and addressing the unique challenges of VCSELs.