English(EN) The Complexity of Verifying Feedforward Neural Networks in Quantised Settings

探索量化设置下神经网络验证的复杂性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-29 04:00

研究人员分析了在使用量化设置时验证前馈神经网络（FNN）的计算复杂性。他们将FNN分为有理数、量化和动态量化类型，并同时考虑了线性规划（LP）和位向量（BV）规范。对于具有固定精度的量化FNN，LP和BV规范的验证仍然是NP完全问题。对于具有BV规范的动态量化FNN，在先前的PSPACE-hardness发现的基础上，建立了新的上限。 AI

排序理由这是一篇研究论文，详细介绍了与神经网络相关的理论计算复杂性发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

arXiv

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇研究论文，详细介绍了与神经网络相关的理论计算复杂性发现。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 104 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Eric Alsmann, Martin Lange, Marco S\"alzer · 2026-05-29 04:00

量化环境下前馈神经网络验证的复杂性

arXiv:2605.29537v1 Announce Type: cross Abstract: We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs with exact rational weights, quantised FNNs whose …

本文如何被排名

报道来源 [1]

量化环境下前馈神经网络验证的复杂性

相关实体

相关话题