Loop Corrections to the Training and Generalization Errors of Random Feature Models
Researchers derive loop corrections to training and generalization errors in random feature models, extending beyond mean-kernel approximation using statistical physics methods.
Excerpt
We investigate random feature models in which neural networks sampled from a prescribed initialization ensemble are frozen and used as random features, with only the readout weights optimized. Adopting a statistical-physics viewpoint, we study the training, test, and generalization errors beyond the mean-kernel approximation. Since the predictor is a nonlinear functional of the induced random kernel, the ensemble-averaged errors depend not only on the mean kernel but also on higher-order fluctuation statistics. Within an effective field-theoretic framework, these finite-width contributions naturally appear as loop corrections. We derive the loop corrections to the training, test, and generalization errors, obtain their scaling laws, and support the theory with experimental verification.
Read at source: https://arxiv.org/abs/2604.12827v1