CHAMP: Coherent Hardware-Aware Magnitude Pruning of Integrated Photonic Neural Networks

Abstract

We propose a novel hardware-aware magnitude pruning technique for coherent photonic neural networks. The proposed technique can prune 99.45% of network parameters and reduce the static power consumption by 98.23% with a negligible accuracy loss.

This paper has been accepted for oral presentation at the IEEE/OPTICA Optical Fiber Communication Conference (OFC) 2022 and will appear in OFC proceedings