The strong lottery ticket hypothesis has highlighted the potential for training deep neural networks by pruning, which has inspired interesting practical and theoretical insights into how neural networks can represent functions. For networks with ReLU activation functions, it has been proven that a target network with depth L can be approximated by the subnetwork of a randomly initialized neural network that has double the target’s depth 2L and is wider by a logarithmic factor. We show that a depth L + 1 network is sufficient. This result indicates that we can expect to find lottery tickets at realistic, commonly used depths while only requiring logarithmic overparametrization. Our novel construction approach applies to a large class of
activation functions and is not limited to ReLUs.
History
Preferred Citation
Rebekka Burkholz. Most Activation Functions Can Win the Lottery Without Excessive Depth. In: Conference on Neural Information Processing Systems (NeurIPS). 2022.
Primary Research Area
Trustworthy Information Processing
Name of Conference
Conference on Neural Information Processing Systems (NeurIPS)
Legacy Posted Date
2022-10-12
Open Access Type
Green
BibTeX
@inproceedings{cispa_all_3803,
title = "Most Activation Functions Can Win the Lottery Without Excessive Depth",
author = "Burkholz, Rebekka",
booktitle="{Conference on Neural Information Processing Systems (NeurIPS)}",
year="2022",
}