mlsanityData to 7 Oct 2026

RECLAIM: Cyclic Causal Discovery Amid Measurement Noise

arXiv 2603.20585 ↗First posted 21 Mar 2026cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Uncovering causal relationships is a fundamental problem across science and engineering. However, most existing causal discovery methods assume acyclicity and direct access to the system variables -- assumptions that fail to hold in many real-world settings. For instance, in genomics, cyclic regulatory networks are common, and measurements are often corrupted by instrumental noise. To address these challenges, we propose RECLAIM, a causal discovery framework that natively handles both cycles and measurement noise. RECLAIM learns the causal graph structure by maximizing the likelihood of the observed measurements via expectation-maximization (EM), using residual normalizing flows for tractable likelihood computation. We consider two measurement models: (i) Gaussian additive noise, and (ii) a linear measurement system with additive Gaussian noise. We provide theoretical consistency guarantees for both the settings. Experiments on synthetic data and real-world protein signaling datasets demonstrate the efficacy of the proposed method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 42 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

17 of 42 references.

References · 17

  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  2. 2018Invertible Residual Networkscited by 364
  3. 2019Residual Flows for Invertible Generative Modelingcited by 256
  4. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  5. 2016Foundations of Structural Causal Models with Cycles and Latent Variablescited by 134
  6. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  7. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  8. 2014Constraint-based Causal Discovery from Multiple Interventions over Overlapping Variable Setscited by 48
  9. 2013A Discovery Algorithm for Directed Cyclic Graphscited by 33
  10. 2013The Bayesian Structural EM Algorithmcited by 26
  11. 2023Multi-Domain Causal Representation Learning via Weak Distributional Invariancescited by 23
  12. 2023NODAGS-Flow: Nonlinear Cyclic Causal Structure Learningcited by 20
5 more
  1. 2020Structure Learning for Cyclic Linear Causal Modelscited by 13
  2. 2019Anchored Causal Inference in the Presence of Measurement Errorcited by 11
  3. 2025Differentiable Cyclic Causal Discovery Under Unmeasured Confounderscited by 4
  4. 2018Sparse semiparametric canonical correlation analysis for data of mixed typescited by 3
  5. 2024MissNODAG: Differentiable Cyclic Causal Graph Learning from Incomplete Datacited by 1

Built on by

Not cited yet.