Non-linear Equalization in 112 Gb/s PONs Using Kolmogorov-Arnold Networks

We investigate Kolmogorov-Arnold networks (KANs) for non-linear equalization of $112 \mathrm{~Gb} / \mathrm{s}$ PAM4 passive optical networks (PONs). Using pruning and extensive hyperparameter search, we outperform linear equalizers and convolutional neural networks at low computational complexity.