Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients.

Dohyung Kim Junghyup Lee Jeimin Jeon Jaehyeon Moon Bumsub Ham

Published in: CoRR (2024)

Keyphrases

fixed point
quantization error
sufficient conditions
belief propagation
training set
reconstruction error
dynamical systems
error diffusion
supervised learning
visual words
feature extraction
additive noise
bag of words
graphical models
motion estimation
preprocessing
computer vision