ε-softmax, which adds a constant to the largest softmax probability and renormalizes, is claimed to make any loss noise-tolerant, but the required δ-condition is false for cross-entropy, so the theoretical promise is not met.
Asymmetric loss functions for learning with noisy labels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
ε-softmax, which adds a constant to the largest softmax probability and renormalizes, is claimed to make any loss noise-tolerant, but the required δ-condition is false for cross-entropy, so the theoretical promise is not met.