# Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability

Source: [Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability](<https://www.sota2.com/research/paper/6a30d91dd33dfb23e783d2dc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-17T05:00:21.724Z

Authors: Abdul-Rauf Nuhu, Parham M. Kebria, Vahid Hemmati, Mahmoud N. Mahmoud, Edward Tunstel, Abdollah Homaifar

Published: 2026-06-15T15:55:22.000Z

## Abstract

Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications. Robustness-based generalization bounds have gained attention as a principled way to link robustness properties to generalization performance, often in a data-dependent manner. However, most existing bounds suffer from vacuousness in practical settings, yielding loose upper bounds that greatly exceed the actual error rates and limiting their usefulness for real-world evaluation. While this issue is often attributed to the uncertainty term, a substantial part of the problem originates from the robustness term itself, particularly for the 0-1 loss. Existing approaches typically treat the robustness term as a global measure, ignoring its variation across different sub-regions of the input space. In this work, we propose a generalization bound that addresses this limitation by scaling the robustness term according to the number of stable and unstable samples within each sub-region. Our bounds incorporate both data- and model-dependent factors while maintaining practical relevance (yielding tighter upper bounds on true error). Experiments on models trained on the ImageNet dataset show that our bounds remain consistently non-vacuous and achieve the tightest estimates among existing methods, closely aligning with empirical performance across a range of robust deep neural networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet 1k (test) (Sensitivity Analysis)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-sensitivity-analysis.md>): Image Classification; ImageNet 1k (test); Top-1 Error Rate: not recorded.

- [Image Classification on ImageNet (val) (Error@1 and Bounds)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-error-at-1-and-bounds.md>): Image Classification; ImageNet (val); Top-1 Error: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.16883>)

[PDF](<https://arxiv.org/pdf/2606.16883.pdf>)
