Using previous checkpoint values as LSTM context for arithmetic coding reduces compressed checkpoint size by 14% to 31% over ExCP on ViT-L32 and Pythia-410M, with the coding stage lossless.
Delta-dnn: efficiently compressing deep neural networks via exploiting floats similarity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
An Efficient Compression of Deep Neural Network Checkpoints Based on Prediction and Context Modeling
Using previous checkpoint values as LSTM context for arithmetic coding reduces compressed checkpoint size by 14% to 31% over ExCP on ViT-L32 and Pythia-410M, with the coding stage lossless.