A Generalized Lottery Ticket Hypothesis
Abstract
We introduce a generalization to the lottery ticket hypothesis in which the notion of "sparsity" is relaxed by choosing an arbitrary basis in the space of parameters. We present evidence that the original results reported for the canonical basis continue to hold in this broader setting. We describe how structured pruning methods, including pruning units or factorizing fully-connected layers into products of low-rank matrices, can be cast as particular instances of this "generalized" lottery ticket hypothesis. The investigations reported here are preliminary and are provided to encourage further research along this direction.
Cite
@article{arxiv.2107.06825,
title = {A Generalized Lottery Ticket Hypothesis},
author = {Ibrahim Alabdulmohsin and Larisa Markeeva and Daniel Keysers and Ilya Tolstikhin},
journal= {arXiv preprint arXiv:2107.06825},
year = {2021}
}
Comments
Workshop on Sparsity in Neural Networks: Advancing Understanding and Practice (SNN'21). Updates: New curve on Figure 2(left) and discussion on Li et al