English

Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning

Machine Learning 2023-01-10 v2

Abstract

We consider the problem of model compression for deep neural networks (DNNs) in the challenging one-shot/post-training setting, in which we are given an accurate trained model, and must compress it without any retraining, based only on a small amount of calibration input data. This problem has become popular in view of the emerging software and hardware support for executing models compressed via pruning and/or quantization with speedup, and well-performing solutions have been proposed independently for both compression approaches. In this paper, we introduce a new compression framework which covers both weight pruning and quantization in a unified setting, is time- and space-efficient, and considerably improves upon the practical performance of existing post-training methods. At the technical level, our approach is based on an exact and efficient realization of the classical Optimal Brain Surgeon (OBS) framework of [LeCun, Denker, and Solla, 1990] extended to also cover weight quantization at the scale of modern DNNs. From the practical perspective, our experimental results show that it can improve significantly upon the compression-accuracy trade-offs of existing post-training methods, and that it can enable the accurate compound application of both pruning and quantization in a post-training setting.

Keywords

Cite

@article{arxiv.2208.11580,
  title  = {Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning},
  author = {Elias Frantar and Sidak Pal Singh and Dan Alistarh},
  journal= {arXiv preprint arXiv:2208.11580},
  year   = {2023}
}

Comments

Published at NeurIPS 2022

R2 v1 2026-06-25T01:56:15.212Z