DLRS adjusts the learning rate per epoch from the normalized first-to-last batch loss slope, and the authors report faster convergence on PINN and image classification benchmarks.
write newline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
DLRS adjusts the learning rate per epoch from the normalized first-to-last batch loss slope, and the authors report faster convergence on PINN and image classification benchmarks.