375 citations · 405 across the 17 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024★ 1 cited
Towards Accurate and Efficient Sub-8-Bit Integer Training
Wenjin Guo, Donglai Liu, Weiying Xie +7
Neural network training is a memory- and compute-intensive task. Quantization, which enables low-bitwidth formats in training, can significantly mitigate the workload. To reduce qu…
cs.LG2023
Physics Inspired Criterion for Pruning-Quantization Joint Learning
Weiying Xie, Xiaoyi Fan, Xin Zhang +3
Pruning-quantization joint learning always facilitates the deployment of deep neural networks (DNNs) on resource-constrained edge devices. However, most existing methods do not joi…