Runge-Kutta optimizers adapted with momentum, preconditioning, or adaptive learning rates can close the large-batch generalization gap and match Adam on small MLP workloads.
Stochastic runge-kutta methods and adaptive sgd-g2 stochastic gradient descent
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
-
Learning by solving differential equations
Runge-Kutta optimizers adapted with momentum, preconditioning, or adaptive learning rates can close the large-batch generalization gap and match Adam on small MLP workloads.