---
title: "Leveraging Over-Parameterization to Improve the Verifiability of Neural Networks"
authors:
  - "Andrea Gimelli"
  - "Luca Oneto"
  - "Armando Tacchella"
doi: "10.24963/ijcai.2026/66"
url: "https://ijcai.org/proceedings/2026/66"
pdf: "https://ijcai.org/proceedings/2026/0066.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "580-589"
track: "Main Track"
keywords:
  - "Machine Learning: Deep learning architectures"
  - "AI Ethics, Trust, Fairnes: Safety and robustness"
---

# Leveraging Over-Parameterization to Improve the Verifiability of Neural Networks

Andrea Gimelli, Luca Oneto, Armando Tacchella

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 580-589. DOI: [10.24963/ijcai.2026/66](https://doi.org/10.24963/ijcai.2026/66)

## Abstract

Over-parameterized neural networks, i.e., models with excess
capacity that can fit training data exactly, have demonstrated superior
generalization performance compared to classical models with balanced
capacity. Nevertheless, their deployment in safety-critical domains re-
mains severely constrained by their susceptibility to, e.g., natural per-
turbations and adversarial manipulations. Verification techniques can
solve such problems, but the computational cost of these methods of-
ten scales poorly, specifically when applied to large models. In this work,
we demonstrate that over-parameterization can be exploited not merely
to enhance generalization, but also to mitigate neuron instability, one of
the parameters affecting the efficiency of verification. Our experimental
findings suggest that over-parameterization may serve as a crucial mech-
anism for reconciling the long-standing trade-off between generalization
and verifiability of neural networks.