EDL learns a transferable classification loss from unlimited synthetic data via evolutionary optimization and a ranking-consistency objective, serving as a competitive drop-in replacement for cross-entropy on CIFAR-10 with ResNet models.
Linear hinge loss and average mar- gin
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamics
EDL learns a transferable classification loss from unlimited synthetic data via evolutionary optimization and a ranking-consistency objective, serving as a competitive drop-in replacement for cross-entropy on CIFAR-10 with ResNet models.