4 papers · 1 filter
ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training
Jie Ji, Gen Li, Kaiyuan Deng +2
Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environm…
FairSAM: Fair Classification on Corrupted Image Data Through Sharpness-Aware Minimization
Yucong Dai, Jie Ji, Xiaolong Ma +1
Image classification models trained on clean data often degrade sharply when exposed to corrupted test or deployment data, such as images with impulse noise, Gaussian noise, or env…
Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Mingyu Cao, Gen Li, Jie Ji +6
Mixture-of-Experts (MoE) has garnered significant attention for its ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does…
Integrating Fairness and Model Pruning Through Bi-level Optimization
Yucong Dai, Gen Li, Feng Luo +2
Deep neural networks have achieved exceptional results across a range of applications. As the demand for efficient and sparse deep learning models escalates, the significance of mo…