Investigating the Not-So-Obvious Effects of Structured Pruning

Abstract

Structured pruning is a popular method to reduce the cost of convolutional neural networks. However, depending on the architecture, pruning introduces dimensional discrepancies which prevent the actual reduction of pruned networks and mask their true complexity. Most papers in the literature overlook these issues. We propose a method that systematically solves them and generate an operational network. We show through experiments the gap between the theoretical pruning ratio and the actual complexity revealed by our method.

Publication
ICML 2022 - Hardware-aware efficient training (HAET)