Replacing cross-entropy with f-divergence losses in weak-to-strong generalization gives modest accuracy gains and improved label-noise tolerance, though the paper's theoretical equivalence result is constructed after the fact.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On Weak-to-Strong Generalization and f-Divergence
Replacing cross-entropy with f-divergence losses in weak-to-strong generalization gives modest accuracy gains and improved label-noise tolerance, though the paper's theoretical equivalence result is constructed after the fact.