AdaAct is an optimizer that scales steps by activation variance rather than gradient variance, and it reports SGD-level accuracy with Adam-level speed on image benchmarks.
Closing the generalization gap of adaptive gradient methods in training deep neural networks
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
unclear 1representative citing papers
citing papers explorer
-
An Adaptive Method Stabilizing Activations for Enhanced Generalization
AdaAct is an optimizer that scales steps by activation variance rather than gradient variance, and it reports SGD-level accuracy with Adam-level speed on image benchmarks.