AI RESEARCH
Faster Verified Explanations for Neural Networks
arXiv CS.LG
•
ArXi:2512.00164v2 Announce Type: replace Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations.