发表机构
Heisenberg Research Center; Huawei Technologies Duesseldorf GmbH; Center for Computational Simulation, Universidad Politécnica de Madrid(海森堡研究中心; 华为技术杜塞尔多夫有限公司; 马德里理工大学计算模拟中心)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出利用全连接张量网络及核范数正则化键修正,从离散概率分布恢复因果DAG的道德图,证明零误差时有效图恰为道德图,并给出近似情形的恢复界。
AI 中文摘要
我们提出了一种从离散变量概率分布中恢复因果有向无环图(DAG)的道德图的方法,该方法使用全连接张量网络(FCTNs),并结合核范数正则化的键修正。每个键矩阵被参数化为基线全一矩阵加上低秩修正 $C_{ij} = U_{ij}V_{ij}^\top$,通过因子上的变分Frobenius范数惩罚实现修正的核范数,该惩罚将不必要的键驱动至零。我们证明,在忠实性、正性以及局部张量架构的无隐式重路由假设下,**每个**具有零重构误差 $\varepsilon = 0$ 的最优FCTN的有效图恰好等于道德图。对于近似情形($\varepsilon > 0$),我们利用条件互信息的Fannes-Audenaert连续性提供了显式的恢复界,并推导了正则化参数 $\beta$ 的充分条件。有效图直接从优化后的键矩阵中读取。
英文摘要
We present a method for recovering the moral graph of a causal DAG from a probability distribution over discrete variables, using fully connected tensor networks (FCTNs) with nuclear-norm-regularized bond corrections. Each bond matrix is parameterized as a baseline all-ones matrix plus a low-rank correction $C_{ij} = U_{ij}V_{ij}^\top$, and the nuclear norm of the correction implemented via the variational Frobenius norm penalty on the factors drives unnecessary bonds to zero. We prove that under faithfulness, positivity, and a no-implicit-rerouting assumption on the local tensor architecture, \textbf{every} optimal FCTN with zero reconstruction error $\varepsilon = 0$ has effective graph exactly equal to the moral graph. For the approximate regime ($\varepsilon > 0$), we provide explicit recovery bounds using the Fannes-Audenaert continuity of conditional mutual information, and derive a sufficient condition on the regularization parameter $β$. The effective graph is read directly from the optimized bond matrices.
Comments24 pages