← Back to all news
arXiv AI By Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Canlin Zhang, Xiuwen Liu

Neural Expansion: A Unified Mechanism for How Deep Neural Networks Generalize

Read the original on arXiv AI →

The paper introduces Neural Expansion, a geometric framework that explains how deep neural networks generalize by expanding directionally-selective ray coverage in input space. It defines Generalization Intervals (GIs) to measure stable prediction regions around training samples and shows through experiments that training progressively enlarges this coverage, especially along directions with low Jacobian singular values. This expansion accounts for correct test predictions, adversarial robustness, and handling of mislabeled or out-of-distribution data, offering a mechanistic complement to existing global theories.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 1

Revisiting the Volume Hypothesis

arXiv:2606. 31282v1 Announce Type: new Abstract: Modern deep neural networks often contain far more parameters than needed to fit their training data, yet they achieve impressive generalization.

By Ari Pakman, Lior Kreimer, Yakir Berchenko
safety
More like this →
arXiv Machine Learning
Sep 25

Pointwise Generalization in Deep Neural Networks

The paper introduces a pointwise generalization theory for fully connected deep neural networks, using a pointwise Riemannian Dimension derived from eigenvalues of learned feature representations across layers. This framework provides hypothesis-dependent, representation-aware generalization bounds that are significantly tighter than traditional size- or norm-based approaches, both theoretically and experimentally. The authors analytically identify structural properties that explain deep networks’ tractability and empirically show that the pointwise Riemannian Dimension captures feature compression, over‑parameterization effects, and optimizer bias.

By Shaojie Li, Yunbei Xu
safety
More like this →