arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.01564cs.LGcs.NAcs.NEmath.NA
收藏

半代数神经网络:从根到表示

Semialgebraic Neural Networks: From roots to representations

Rice University(莱斯大学);University of Helsinki(赫尔辛基大学)

S. David Mis, Matti Lassas, Maarten V. de Hoop

AI总结:

提出半代数神经网络(SANNs),通过将函数图像编码为分段多项式的核并执行同伦延拓方法,能够精确表示任意有界(含不连续)半代数函数,且支持传统深度学习训练。

摘要:

科学计算中的许多数值算法——特别是在数值线性代数、PDE模拟和逆问题等领域——产生的输出可由半代数函数表示;即计算所得函数的图像可由有限个多项式等式和不等式描述。在本研究中,我们提出了半代数神经网络(SANNs),这是一种能够表示任何有界半代数函数,并根据程序员选择的数值ODE求解器精度进行计算的网络架构。在概念上,我们将所学函数的图像编码为分段多项式的核,该多项式选自一类其根可使用特定同伦延拓方法求值的函数。我们通过构造证明,SANN架构能够执行此延拓方法,从而评估所学到的半代数函数。此外,通过在目标函数的每个连通分量上执行延拓方法,该架构甚至能精确表示不连续的半代数函数。最后,我们提供了这些网络的应用示例,并表明它们可通过传统的深度学习技术进行训练。

英文摘要:

Many numerical algorithms in scientific computing -- particularly in areas like numerical linear algebra, PDE simulation, and inverse problems -- produce outputs that can be represented by semialgebraic functions; that is, the graph of the computed function can be described by finitely many polynomial equalities and inequalities. In this work, we introduce Semialgebraic Neural Networks (SANNs), a neural network architecture capable of representing any bounded semialgebraic function, and computing such functions up to the accuracy of a numerical ODE solver chosen by the programmer. Conceptually, we encode the graph of the learned function as the kernel of a piecewise polynomial selected from a class of functions whose roots can be evaluated using a particular homotopy continuation method. We show by construction that the SANN architecture is able to execute this continuation method, thus evaluating the learned semialgebraic function. Furthermore, the architecture can exactly represent even discontinuous semialgebraic functions by executing a continuation method on each connected component of the target function. Lastly, we provide example applications of these networks and show they can be trained with traditional deep-learning techniques.

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。

↑