6 APPENDIX

This appendix provides the mathematical proofs of the theoretical results and additional experiment results of our paper "Neuron Merging: Compensating for Pruned Neurons," accepted at 34th The overall derivation is the same as Section 3.1. If there exists a column with more than one strictly positive entry, then Eq. 13a does not For simple notation, subscript i is omitted. In Table 4, we present the test results of VGG-16 and ResNet-34 on ImageNet. ResNet-34, we prune all convolution layers in equal proportion. For example, '1-1' indicates the first pruned layer in the first residual block.