Initializing Adam's second-order moment estimate to a non-zero value, rather than the default zero, reduces early training instability and improves generalization across several deep learning tasks.
Why adam outperforms gradient descent on language models: A heavy-tailed class imbalance problem
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Revisiting the Initial Steps in Adaptive Gradient Descent Optimization
Initializing Adam's second-order moment estimate to a non-zero value, rather than the default zero, reduces early training instability and improves generalization across several deep learning tasks.