Research map / Learning theory and algorithms / Prediction and decision losses

Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation

NeurIPS 2025 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces H2V, a validation method for local robustness of neural networks against geometric perturbations, using Hilbert space-filling curves and Hölder optimisation.

Problem

Validating local robustness of neural networks against geometric perturbations, where dense-perturbation-space verification methods are not scalable.

Approach

Recasts multi-dimensional geometric perturbation search into a single-dimensional problem via a Hilbert space-filling curve, then iteratively refines the search with Hölder optimisation.

Closest papers by meaning

• Probably Approximately Global Robustness Certification (ICML 2025 · similarity 0.87)
• Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation (CVPR 2024 · similarity 0.86)
• Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone (CVPR 2025 · similarity 0.86)
• LEVIS: Large Exact Verifiable Input Spaces for Neural Networks (ICML 2025 · similarity 0.85)
• VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees (ICML 2024 · similarity 0.85)
• Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks (NeurIPS 2026 · similarity 0.85)