Exploring the Performance of Pruning Methods in Neural Networks: An Empirical Study of the Lottery Ticket Hypothesis
Not on the map. Why?
Abstract (arXiv)
In this paper, we explore the performance of different pruning methods in the context of the lottery ticket hypothesis. We compare the performance of L1 unstructured pruning, Fisher pruning, and random pruning on different network architectures and pruning scenarios. The experiments include an evaluation of one-shot and iterative pruning, an examination of weight movement in the network during pruning, a comparison of the pruning methods on networks of varying widths, and an analysis of the performance of the methods when the network becomes very sparse. Additionally, we propose and evaluate a new method for efficient computation of Fisher pruning, known as batched Fisher pruning.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 10 of its 22 references that are in the map. First posted on arXiv 26 Mar 2023.
Builds on
10 of 22 references.
References · 10
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
- 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 637
- 2020Comparing Rewinding and Fine-tuning in Neural Network Pruningcited by 240
- 2020The Early Phase of Neural Network Trainingcited by 115
- 2020Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNscited by 104
- 2018Faster gaze prediction with dense networks and Fisher pruningcited by 94
- 2020The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Modelscited by 91
- 2022The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Trainingcited by 85
- 2019Stabilizing the Lottery Ticket Hypothesiscited by 37
- 2018Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networkscited by 10
Built on by
Citing papers per year: 2025: 2.
2 papers.