The paper introduces SURE-Ridge, a closed‑form estimator for recovering the directed acyclic graph of an equal‑variance linear Gaussian structural equation model. It performs parallel node‑wise regressions with regularization parameters selected via Stein's unbiased risk estimate and then applies adaptive thresholding to produce a DAG from a soft adjacency matrix. Experiments show that SURE‑Ridge attains the lowest structural Hamming distance in small‑sample settings and the fastest run time across all tested sample sizes compared to NOTEARS, DAGMA, and GBNSL.
By Sambit Mishra, Urbashi Mitra
arXiv:2609.30643v1 Announce Type: new
Abstract: We consider the problem of learning the underlying causal directed acyclic graph (DAG) structure corresponding to a structural equation model (SEM) wit...
By Anamitra Chaudhuri, Anirban Bhattacharya, Yang Ni
arXiv:2601.01368v2 Announce Type: replace
Abstract: Score-based causal discovery in the presence of unobserved confounders requires both a consistent scoring criterion and an efficient search over gr...
By Mujin Zhou, Ignavier Ng, Junzhe Zhang
arXiv:2609. 18535v1 Announce Type: new Abstract: Causal discovery aims to recover causal relationships from observed data.
By Weijian Yu, Jean Honorio
The paper introduces a method for learning causal structures in linear Gaussian models that may contain directed cycles and an unknown number of latent confounders, bounded by a maximum. It derives the covariance of observed variables, defines marginal quasi-equivalence to identify when different models produce the same observational distributions, and formulates structure learning as a minimization of Gaussian negative log-likelihood with a complexity penalty counting edges and latent variables. Using Bernoulli gates to parameterize edge and latent inclusion, the authors obtain a closed‑form differentiable objective whose expected value shares the same global optimum as the discrete problem, and demonstrate experimentally that this approach yields lower recovery error than prior methods.
By Sadegh Khorasani, Ali Najar, Saber Salehkaleybar, Negar Kiyavash
arXiv:2607. 03364v1 Announce Type: cross Abstract: We propose \textbf{CaSPECT}, a causal spectral clustering framework for discovering causally homogeneous subgroups from observational data.
By Arghya Pratihar, Shinjon Chakraborty, Swagatam Das
arXiv:2607. 05984v1 Announce Type: new Abstract: Recovering the exact directed acyclic graph (DAG) in linear non-Gaussian acyclic models with latent confounders (LvLiNGAM) remains a challenging problem.
By Ming Cai, Hisayuki Hara
The paper introduces Cluster-DAGs as a flexible prior knowledge framework to improve causal discovery. It presents two modified constraint‑based algorithms, Cluster‑PC and Cluster‑FCI, tailored for fully and partially observed data. Experiments on simulated data show that these methods outperform baseline algorithms that lack prior knowledge.
By Jan Marco Ruiz de Vargas, Kirtan Padh, Niki Kilbertus
arXiv:2607. 11510v1 Announce Type: new Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs).
By Yikang Chen, Zhengkang Guan, Haoyuan Qian, Peng Cui, Yi Yang, Kun Kuang
arXiv:2609.27256v1 Announce Type: cross
Abstract: We study causal discovery where each node is a random function. Previous studies on this topic rely on structural assumptions, e.g., linearity or non...
By Keyu Li, Ruoxu Tan
arXiv:2608. 04930v1 Announce Type: cross Abstract: Bayesian causal discovery seeks to determine the posterior distribution of causal theories, which are interpreted as directed acyclic graphs (DAGs) that explain the observed data.
By Shrenik Zinage
arXiv:2606. 03227v1 Announce Type: new Abstract: Causal discovery with instantaneous effects in multivariate time series is challenging, as the instantaneous structure must be acyclic.
By Tong Zhao, Ce Guo, Wayne Luk, Emil Lupu, Ray Dipojjwal