A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to reducing the number of parameters in a DNN. In this paper, we propose a framework for pruning DNNs based on a population-based global optimization method. This framework can use any pruning objective function. As a case study, we propose a simple but efficient objective function based on the concept of energy-based models. Our experiments on ResNets, AlexNet, and SqueezeNet for the CIFAR-10 and CIFAR-100 datasets show a pruning rate of more than 50% of the trainable parameters with approximately <5% and <1% drop of Top-1 and Top-5 classification accuracy, respectively.
@article{arxiv.2102.13188,
title = {A Framework For Pruning Deep Neural Networks Using Energy-Based Models},
author = {Hojjat Salehinejad and Shahrokh Valaee},
journal= {arXiv preprint arXiv:2102.13188},
year = {2021}
}
Comments
This paper is accepted for presentation at IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2021. arXiv admin note: text overlap with arXiv:2006.04270, arXiv:2102.05437