Newest papers

Tractable Inference with Kolmogorov-Arnold Networks

Juan Diego Toscano, Sascha Ranftl, Zhiwei Gao, Li-Lian Wang, George Em Karniadakis · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29909 · open-access PDF

Chinese

计算科学中的机器学习替代品通常不仅需要准确的预测,而且还需要预测,变异,保存整数和正常化常数。 传统的神经网络,包括科尔莫戈洛夫 - 阿诺德网络(KANs),通常通过蒙特卡洛样本采样或多维平方来评估这些数量,使重复推断成本昂贵,尤其是在高维度中。

Machine translation (Meta M2M100); the English original follows.

Abstract

Machine-learning surrogates in computational science often require not only accurate predictions but also expectations, variances, conserved integrals, and normalization constants. Conventional neural networks, including Kolmogorov--Arnold networks (KANs), generally evaluate these quantities through Monte Carlo sampling or multidimensional quadrature, making repeated inference costly, particularly in high dimensions. We introduce KANs with Tractable Operators for Uncertainty and Constraints (TOUCKANs), whose finite-degree polynomial outer functions yield a decomposable sum--product representat

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange