PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training

By Sangkug Lym, Esha Choukse, Siavash Zangeneh, Wujie Wen, Mattan Erez, Sujay Shanghavi. 2019

13 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Tao Lin
2. Sebastian U. Stich
3. Martin Jaggi
4. Jonathan Frankle
5. Yuang Jiang
6. Gintare Karolina Dziugaite
7. Michael Carbin
8. Daniel M. Roy

Citations in the corpus

• Dynamic Model Pruning with Feedback (2020, background): “We do believe a better filter selection scheme (Ye et al., 2018; He et al., 2019; Lym et al., 2019) could further improve the results but we leave this exploration for the future work.”
• Model Pruning Enables Efficient Federated Learning on Edge Devices (2019, methodology): “We note that there also exist pruning techniques where the resulting pruned model is constrained on using dense matrix representation [23], in which case sparse matrix computation is not needed.”
• Stabilizing the Lottery Ticket Hypothesis (2019, background): “…in its own right, including pruning before training (Lee et al., 2019), pruning throughout training (Zhu and Gupta, 2017; Gale et al., 2019; Lym et al., 2019; Molchanov et al., 2017; Louizos et al., 2018; Narang et al., 2017), and maintaining a sparse network with dynamic structure (Bellec…”