English

Considering Layerwise Importance in the Lottery Ticket Hypothesis

Computer Vision and Pattern Recognition 2023-02-23 v1 Machine Learning

Abstract

The Lottery Ticket Hypothesis (LTH) showed that by iteratively training a model, removing connections with the lowest global weight magnitude and rewinding the remaining connections, sparse networks can be extracted. This global comparison removes context information between connections within a layer. Here we study means for recovering some of this layer distributional context and generalise the LTH to consider weight importance values rather than global weight magnitudes. We find that given a repeatable training procedure, applying different importance metrics leads to distinct performant lottery tickets with little overlapping connections. This strongly suggests that lottery tickets are not unique

Cite

@article{arxiv.2302.11244,
  title  = {Considering Layerwise Importance in the Lottery Ticket Hypothesis},
  author = {Benjamin Vandersmissen and Jose Oramas},
  journal= {arXiv preprint arXiv:2302.11244},
  year   = {2023}
}
R2 v1 2026-06-28T08:46:36.855Z