A Survey of Lottery Ticket Hypothesis
It addresses challenges in neural network pruning for researchers, but is incremental as it synthesizes existing work.
This survey examines the Lottery Ticket Hypothesis, which proposes that sparse subnetworks in dense neural networks can outperform the original models, and it identifies open issues like efficiency and scalability while providing a platform for future research.
The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i.e., winning tickets) that can achieve even better performance than the original model when trained in isolation. While LTH has been proved both empirically and theoretically in many works, there still are some open issues, such as efficiency and scalability, to be addressed. Also, the lack of open-source frameworks and consensual experimental setting poses a challenge to future research on LTH. We, for the first time, examine previous research and studies on LTH from different perspectives. We also discuss issues in existing works and list potential directions for further exploration. This survey aims to provide an in-depth look at the state of LTH and develop a duly maintained platform to conduct experiments and compare with the most updated baselines.