Optimal softmax temperature is analytically determined by feature dimensionality, adjusted by fitted coefficients and batch norm for model- and domain-robust classification.
When does label smoothing help? In Advances in Neural Information Processing Systems, volume 32
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification
Optimal softmax temperature is analytically determined by feature dimensionality, adjusted by fitted coefficients and batch norm for model- and domain-robust classification.