Despite its potential benefits, applying DST to GANs presents challenges due to the adversarial nature of the training process.

Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference.

Surprisingly, we find that most of the studied methods yield similar results.

However, the training of a sparse DNN encounters great challenges in achieving optimal generalization ability despite the efforts from the state-of-the-art sparse training methodologies. To unravel the mysterious reason behind the difficulty of sparse training, we connect network sparsity with the structure of neural loss functions and identify that the cause of such difficulty lies in a chaotic loss surface.

Sparse training stands as a landmark approach in addressing the considerable training resource demands imposed by the continuously expanding size of Deep Neural Networks (DNNs). However, the training of a sparse DNN encounters great challenges in achieving optimal generalization ability despite the efforts from the state-of-the-art sparse training methodologies. To unravel the mysterious reason behind the difficulty of sparse training, we connect the network sparsity with neural loss functions structure, and identify the cause of such difficulty lies in chaotic loss surface. In light of such revelation, we propose $S^{2} - SAM$, characterized by a **S**ingle-step **S**harpness_**A**ware **M**inimization that is tailored for **S**parse training.