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.
On the convergence of a class of adam-type algorithms for non-convex optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 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.