Unmasking the Lottery Ticket Hypothesis
Deep Learning
Neural Networks
Network Pruning
Machine Learning
The research paper delves into the detailed workings of Iterative Magnitude Pruning (IMP) in deep learning, exploring the ‘why’ and ‘how’ of its success in finding sparse subnetworks within larger neural networks.
Read transcript · Original paper
AI-generated voices discussing a paper selected by Arjun Srivastava.
About this paper
The key takeaways for engineers/specialists include understanding the role of the pruning mask in guiding training, the importance of SGD robustness in navigating the error landscape, and the relationship between the Hessian eigenspectrum and the maximum pruning ratio for efficient network pruning.