Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin
Abstract
There have been long-standing controversies and inconsistencies over the experiment setup and criteria for identifying the "winning ticket" in literature. To reconcile such, we revisit the definition of lottery ticket hypothesis, with comprehensive and more rigorous conditions. Under our new definition, we show concrete evidence to clarify whether the winning ticket exists across the major DNN architectures and/or applications. Through extensive experiments, we perform quantitative analysis on the correlations between winning tickets and various experimental factors, and empirically study the patterns of our observations. We find that the key training hyperparameters, such as learning rate and training epochs, as well as the architecture characteristics such as capacities and residual connections, are all highly correlated with whether and when the winning tickets can be identified. Based on our analysis, we summarize a guideline for parameter settings in regards of specific architecture characteristics, which we hope to catalyze the research progress on the topic of lottery ticket hypothesis. Our codes are publicly available at: https://github.com/boone891214/sanity-check-LTH.
BibTeX
@inproceedings{
ma2021sanity,
title={Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?},
author={Xiaolong Ma and Geng Yuan and Xuan Shen and Tianlong Chen and Xuxi Chen and Xiaohan Chen and Ning Liu and Minghai Qin and Sijia Liu and Zhangyang Wang and Yanzhi Wang},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=WL7pr00_fnJ}
}