The test error of random-feature ridge regression with arbitrary data augmentation admits a closed-form asymptotic characterization in the proportional regime that depends only on population covariances and augmentation statistics.
arXiv preprint arXiv:2002.12478 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
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.
citing papers explorer
-
Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
The test error of random-feature ridge regression with arbitrary data augmentation admits a closed-form asymptotic characterization in the proportional regime that depends only on population covariances and augmentation statistics.
-
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.