Y Zhang, M Lin, Z Lin, Y Luo, K Li… - Advances in Neural …, 2022 - proceedings.neurips.cc
By forcing N out of M consecutive weights to be non-zero, the recent N: M fine-grained network sparsity has received increasing attention with its two attractive advantages over …
Though network pruning receives popularity in reducing the complexity of convolutional neural networks (CNNs), it remains an open issue to concurrently maintain model accuracy …
Deep learning technology has found a promising application in lightweight model design, for which pruning is an effective means of achieving a large reduction in both model parameters …
Y Zhang, Y Luo, M Lin, Y Zhong, J Xie… - … on machine learning, 2023 - proceedings.mlr.press
We focus on addressing the dense backward propagation issue for training efficiency of N: M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves …
Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for both the entire training process as well as the inference. Dynamic sparse …
Recent innovations on hardware (eg Nvidia A100) have motivated learning N: M structured sparsity masks from scratch for fast model inference. However, state-of-the-art learning …
J Liu, D Tang, Y Huang, L Zhang, X Zeng, D Li… - Proceedings of the …, 2024 - ojs.aaai.org
Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain …
State-of-the-art deep learning models have a parameter count that reaches into the billions. Training, storing and transferring such models is energy and time consuming, thus costly. A …
Despite the remarkable success of Large Language Models (LLMs), the massive size poses significant deployment challenges, particularly on resource-constrained hardware. While …