Lune

NeurIPS2025Top-tier venue

DSCS: Fast CPDAG-Based Verification of Collapsible Submodels in High-Dimensional Bayesian Networks

Wentao Wu, Shiyuan He, Jianhua Guo

Abstract

Bayesian networks (BNs), represented by directed acyclic graphs (DAGs), provide a principled framework for modeling complex dependencies among random variables. As data dimensionality increases into the tens of thousands, fitting and marginalizing a full BN becomes computationally prohibitive—particularly when inference is only needed for a small subset of variables. Estimation-collapsibility addresses this challenge by ensuring that directly fitting a submodel, obtained by ignoring non-essential variables, still yields exact inference on target variables. However, current DAG-based criterion for checking estimation-collapsibility is computationally intensive, involving exhaustive vertex searches and iterative re-movals. Additionally, practical applications typically identify the underlying DAG only up to its Markov equivalence class, represented by a completed partially directed acyclic graph (CPDAG). To bridge this gap, we introduce sequential c -simplicial sets—a novel graphical characterization of estimation-collapsibility directly applicable to CPDAGs. We further propose DSCS, a computationally efficient algorithm for verifying estimation-collapsibility within CPDAG framework that scales effectively to high-dimensional BNs. Extensive numerical experiments demonstrate the practicality, scalability, and efficiency of our proposed approach.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. Causal Discovery with Reinforcement LearningShengyu Zhu, Ignavier Ng, Zhitang ChenICLR 2020 · 285 citations
  2. Directed Acyclic Graph Neural NetworksVeronika Thost, Jie ChenICLR 2021 · 134 citations
  3. Causal normalizing flows: from theory to practiceAdrián Javaloy, Pablo Sánchez-Martín, Isabel ValeraNeurIPS 2023 · 61 citations

Related papers

  1. BayesDAG: Gradient-Based Posterior Inference for Causal DiscoveryYashas Annadani, Nick Pawlowski, Joel Jennings, Stefan Bauer et al.NeurIPS 2023 · 54 citations
  2. Learning Large DAGs by Combining Continuous Optimization and Feedback Arc Set HeuristicsPierre Gillot, Pekka ParviainenAAAI 2022 · 5 citations
  3. BCD Nets: Scalable Variational Approaches for Bayesian Causal DiscoveryChris Cundy, Aditya Grover, Stefano ErmonNeurIPS 2021 · 105 citations
  4. Towards Scalable Bayesian Learning of Causal DAGsJussi Viinikka, Antti Hyttinen, Johan Pensar, Mikko KoivistoNeurIPS 2020 · 49 citations
  5. Structure Learning with Adaptive Random Neighborhood Informed MCMCXitong Liang, Alberto Caron, Samuel Livingstone, Jim E. GriffinNeurIPS 2023 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines