A Framework for Pruning Deep Neural Networks Using Energy-Based Models

Hojjat Salehinejad; Shahrokh Valaee

ICASSP 2021accepted0 citations

A Framework for Pruning Deep Neural Networks Using Energy-Based Models

Abstract

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.

BibTeX

@inproceedings{icassp2021_aframeworkforpru,
  title = {A Framework for Pruning Deep Neural Networks Using Energy-Based Models},
  author = {Hojjat Salehinejad and Shahrokh Valaee},
  booktitle = {ICASSP 2021},
  year = {2021}
}