How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear Gaussian Networks under Latent Confounding

• URL: http://arxiv.org/abs/2607.09449v2
• Date: Thu, 16 Jul 2026 15:06:53 GMT
• Title: How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear Gaussian Networks under Latent Confounding
• Abstract summary: This work focuses on additive latent confounding between exactly two observed variables.<n>We characterize two distinct posterior failure regimes determined by the local structure around the confounded variables.<n>Our findings are supported by exact posterior computations on multiple graph structures.
• Score: 0.7391823486666543
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Bayesian causal discovery is widely used for its ability to quantify epistemic uncertainty over directed acyclic graphs (DAGs) through posterior inference. However, its behaviour under latent confounding remains poorly understood, as existing work typically notes that confounding breaks identifiability without characterising how the posterior distribution over DAGs responds. In this work, we analyse posterior behaviour under latent confounding in linear Gaussian causal models, focusing on additive latent confounding between exactly two observed variables. We derive a critical correlation threshold above which the score function favours graphs with a spurious edge between the confounded variables, and show that this threshold decreases with sample size -- more data lowers the correlation required for the spurious edge to be favoured. Beyond this threshold, we characterize two distinct posterior failure regimes determined by the local structure around the confounded variables. Our findings are supported by exact posterior computations on multiple graph structures, demonstrating both the predicted failure regimes.

Related papers

• SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discovery [0.0]
  SVI-DAG is a structured variational inference approach to causal discovery.<n>It supports expressive and multimodal posterior learning over DAGs.<n>We evaluate SVI-DAG against 5 state-of-the-art Bayesian DAG learning methods.
  arXiv  Detail & Related papers  (2026-08-05T14:56:14Z)
• Discrete Causal Representation Learning [31.812206971607676]
  Causal representation learning seeks to uncover causal relationships among high-level latent variables from low-level, entangled, and noisy observations.<n>We propose a generative framework that models a directed acyclic graph among discrete latent variables, along with a sparse bipartite graph linking latent and observed layers.<n>Under mild conditions, we prove that both the bipartite measurement graph and the latent causal graph are identifiable from the observed data distribution alone.
  arXiv  Detail & Related papers  (2026-03-26T04:28:02Z)
• Consistent DAG selection for Bayesian causal discovery under general error distributions [9.971549076128268]
  We consider the problem of learning the underlying causal structure among a set of variables.<n>The associated errors are independent and allowed to be non-Gaussian.<n>A Bayesian hierarchical model is proposed to identify the true data-generating directed acyclic graph (DAG) structure.
  arXiv  Detail & Related papers  (2025-08-01T18:03:28Z)
• A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation [59.473751744275496]
  Scene Graph Generation (SGG) frameworks typically incorporate a detector to extract relationship features and a classifier to categorize these relationships.<n>Such a causal chain structure can yield spurious correlations between the detector's inputs and the final predictions.<n>We propose reconstructing the causal chain structure into a reverse causal structure, wherein the classifier's inputs are treated as the confounder.
  arXiv  Detail & Related papers  (2025-05-29T13:57:01Z)
• A Meta-Learning Approach to Bayesian Causal Discovery [15.017003416900836]
  Uncertainty over causal structures, such as those obtained from a Bayesian posterior, is often necessary for downstream tasks.<n>Recent works have used meta-learning to view the problem of estimating the maximum a-posteriori causal graph as supervised learning.<n>We propose a Bayesian meta learning model that allows for sampling causal structures from the posterior and encodes these key properties.
  arXiv  Detail & Related papers  (2024-12-21T10:52:56Z)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• Towards Causal Representation Learning and Deconfounding from Indefinite Data [17.793702165499298]
  Non-statistical data (e.g., images, text, etc.) encounters significant conflicts in terms of properties and methods with traditional causal data. We redefine causal data from two novel perspectives and then propose three data paradigms. We implement the above designs as a dynamic variational inference model, tailored to learn causal representation from indefinite data.
  arXiv  Detail & Related papers  (2023-05-04T08:20:37Z)
• BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery [97.79015388276483]
  A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic graph (DAG) Recent advances enabled effective maximum-likelihood point estimation of DAGs from observational data. We propose BCD Nets, a variational framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM.
  arXiv  Detail & Related papers  (2021-12-06T03:35:21Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Variational Causal Networks: Approximate Bayesian Inference over Causal Structures [132.74509389517203]
  We introduce a parametric variational family modelled by an autoregressive distribution over the space of discrete DAGs. In experiments, we demonstrate that the proposed variational posterior is able to provide a good approximation of the true posterior.
  arXiv  Detail & Related papers  (2021-06-14T17:52:49Z)
• Deconfounded Score Method: Scoring DAGs with Dense Unobserved Confounding [101.35070661471124]
  We show that unobserved confounding leaves a characteristic footprint in the observed data distribution that allows for disentangling spurious and causal effects. We propose an adjusted score-based causal discovery algorithm that may be implemented with general-purpose solvers and scales to high-dimensional problems.
  arXiv  Detail & Related papers  (2021-03-28T11:07:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.