Neural Tangent Kernels Under Stochastic Data Augmentation

Joshua DeOliveira; Sajal Chakroborty; Walter Gerych; Elke Rundensteiner

AAAI 2026technical0 citations

Neural Tangent Kernels Under Stochastic Data Augmentation

Joshua DeOliveira, Sajal Chakroborty, Walter Gerych, Elke Rundensteiner

Abstract

The learning dynamics of modern neural networks remain an open problem in deep learning. The Neural Tangent Kernel (NTK) offers an elegant description of training dynamics in the infinite‑width limit, yet its classical formulation assumes a static data set. Modern model training practice departs from this strong assumption through the use of on‑the‑fly data augmentations (e.g. additive noise). In this work, we conduct an NTK-driven analysis of how data transformations affect a neural net

BibTeX

@inproceedings{aaai2026_neuraltangentker,
  title = {Neural Tangent Kernels Under Stochastic Data Augmentation},
  author = {Joshua DeOliveira and Sajal Chakroborty and Walter Gerych and Elke Rundensteiner},
  booktitle = {AAAI 2026},
  year = {2026}
}