研究人员开发了用于神经网络代理模型的新训练正则化器，可直接提高其在混合整数线性规划（MILP）中的可解性。这些正则化器会惩罚诸如big-M常数和不稳定神经元等因素，并明确解决LP松弛差距。实验表明，这些方法在保持精度的同时，可以将MILP求解时间缩短多达四个数量级。 AI
影响 新颖的训练技术有望显著加速使用神经网络作为代理的优化问题。
排序理由 学术论文，介绍了用于神经网络代理模型的新颖训练正则化器。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.22746v1 Announce Type: cross Abstract: ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tractability of the resulting MILP depends on structura…
ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tractability of the resulting MILP depends on structural properties of the network, i.e., the number of b…