Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models.

Clara Na Sanket Vaibhav Mehta Emma Strubell

Published in: EMNLP (Findings) (2022)

Keyphrases

statistical models
data compression
probabilistic model
bayesian framework
data sets
databases
feature selection
expert systems
pairwise
probability distribution
visual perception