AI RESEARCH
ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training
arXiv CS.LG
•
ArXi:2603.13115v1 Announce Type: new Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these constraints by dramatically reducing parameter count and computational overhead. However, existing sparse