2 citations · 5 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 2 cited
Towards Optimal Compression: Joint Pruning and Quantization
Ben Zandonati, Glenn Bucagu, Adrian Alan Pol +3
Model compression is instrumental in optimizing deep neural network inference on resource-constrained hardware. The prevailing methods for network compression, namely quantization…
cs.LG2022★ 1 cited
FIT: A Metric for Model Sensitivity
Ben Zandonati, Adrian Alan Pol, Maurizio Pierini +2
Model compression is vital to the deployment of deep learning on edge devices. Low precision representations, achieved via quantization of weights and activations, can reduce infer…