# BGD-based Adam algorithm for time-domain equalizer in PAM-based optical interconnects

## TL;DR

This paper introduces a novel BGD-based Adam algorithm for designing time-domain equalizers in PAM optical interconnects, achieving fast, stable convergence and improved efficiency over traditional methods.

## Contribution

It is the first to apply BGD-based Adam algorithm to TDE in optical interconnects, enabling globally optimal tap coefficients and parallel processing implementation.

## Key findings

- Effective in 120-Gbit/s PAM8 optical interconnects
- Achieves fast and stable convergence
- Outperforms traditional serial algorithms

## Abstract

To the best of our knowledge, for the first time, we propose adaptive moment estimation (Adam) algorithm based on batch gradient descent (BGD) to design a time-domain equalizer (TDE) for PAM-based optical interconnects. Adam algorithm has been widely applied in the fields of artificial intelligence. For TDE, BGD-based Adam algorithm can obtain globally optimal tap coefficients without being trapped in locally optimal tap coefficients. Therefore, fast and stable convergence can be achieved by BGD-based Adam algorithm with low mean square error. Meanwhile, BGD-based Adam algorithm is implemented by parallel processing, which is more efficient than conventional serial algorithms, such as least mean square and recursive least square algorithms. The experimental results demonstrate that BGD-based Adam feed-forward equalizer works well in 120-Gbit/s PAM8 optical interconnects. In conclusion, BGD-based Adam algorithm shows great potential for converging the tap coefficients of TDE in future optical interconnects.