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.
Label distributionally robust losses for multi-class classification: Consistency, robustness and adaptivity
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
REJECT 1roles
background 1polarities
unclear 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.