Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients

  • Milad AlizadehUniversity of OxfordUniversity of Cambridge
  • Shyam A. TailorUniversity of Cambridge
  • Luisa M ZintgrafUniversity of Oxford
  • Joost van AmersfoortUniversity of Oxford
  • Sebastian FarquharUniversity of Oxford
  • Nicholas Donald LaneUniversity of CambridgeSamsung AI Center, Cambridge
  • Yarin GalUniversity of Oxford

International Conference on Learning Representations (ICLR), 2022

Abstract

Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network while consuming fewer computational resources for training and inference. However, current methods are insufficient to enable this optimization and lead to a large degradation in model performance. In this paper, we identify a fundamental limitation in the formulation of current methods, namely that their saliency criteria look at a single step at the start of training without taking into account the trainability of the network. While pruning iteratively and gradually has been shown to improve pruning performance, explicit consideration of the training stage that will immediately follow pruning has so far been absent from the computation of the saliency criterion. To overcome the short-sightedness of existing methods, we propose Prospect Pruning (ProsPr), which uses meta-gradients through the first few steps of optimization to determine which weights to prune. ProsPr combines an estimate of the higher-order effects of pruning on the loss and the optimization trajectory to identify the trainable sub-network. Our method achieves state-of-the-art pruning performance on a variety of vision classification tasks, with less data and in a single shot compared to existing pruning-at-initialization methods.

Materials

  • PDF
BibTeX
@inproceedings{alizadeh2022prospect,
  title = {{Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients}},
  author = {Alizadeh, Milad and Tailor, Shyam A. and Zintgraf, Luisa M and van Amersfoort, Joost and Farquhar, Sebastian and Lane, Nicholas Donald and Gal, Yarin},
  year = {2022},
  booktitle = {International Conference on Learning Representations (ICLR)}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub