arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.02406math.COcs.CCcs.DMcs.LGmath.OC
收藏

正则拟阵的算术电路与神经网络

Arithmetic Circuits and Neural Networks for Regular Matroids

University of Technology Nuremberg(图恩堡技术大学);Université Libre de Bruxelles(布鲁塞尔自由大学);Freie Universität Berlin(柏林自由大学);University of Twente(埃因霍温大学)

Christoph Hertrich, Stefan Kober, Georg Loho

AI总结:

本文证明了存在大小为 $O(n^3)$ 的电路和 ReLU 神经网络,用于计算正则拟阵的基生成多项式并解决加权基最大化问题,并首次展示了虚拟扩展构形比已知最佳单个扩展构形更高效。

摘要:

我们证明了存在大小为 $O(n^3)$ 的均匀 $(+,\times,/)$-电路,用于计算 $n$ 个元素上正则拟阵的基生成多项式。通过热带化,这意味着存在相同大小的均匀 $(\max,+,-)$-电路和 ReLU 神经网络,用于正则拟阵的加权基最大化。作为线性规划理论中的一个推论,我们得到了一个首个例子,其中取两个扩展构形的差可以比 Aprile 和 Fiorini 已知大小为 $O(n^6)$ 的最佳单个扩展构形更高效。这种差最近被引入为虚拟扩展构形。我们主要结果的证明依赖于正则拟阵的 Seymour 分解的微调版本,该版本使我们能够识别和维护图形子结构,从而对其应用星-网格变换的局部版本。

英文摘要:

We prove that there exist uniform $(+,\times,/)$-circuits of size $O(n^3)$ to compute the basis generating polynomial of regular matroids on $n$ elements. By tropicalization, this implies that there exist uniform $(\max,+,-)$-circuits and ReLU neural networks of the same size for weighted basis maximization of regular matroids. As a consequence in linear programming theory, we obtain a first example where taking the difference of two extended formulations can be more efficient than the best known individual extended formulation for the base polytope of regular matroids of size $O(n^6)$ by Aprile and Fiorini. Such differences have recently been introduced as virtual extended formulations. The proof of our main result relies on a fine-tuned version of Seymour's decomposition of regular matroids which allows us to identify and maintain graphic substructures to which we can apply a local version of the star-mesh transformation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑