mlsanityData to 7 Oct 2026

On the Sample Complexity of Causal Discovery and the Value of Domain Expertise

arXiv 2102.03274 ↗First posted 5 Feb 2021cs.LG stat.APcited by 9

Not on the map. Why?

Abstract (arXiv)

Causal discovery methods seek to identify causal relations between random variables from purely observational data, as opposed to actively collected experimental data where an experimenter intervenes on a subset of correlates. One of the seminal works in this area is the Inferred Causation algorithm, which guarantees successful causal discovery under the assumption of a conditional independence (CI) oracle: an oracle that can states whether two random variables are conditionally independent given another set of random variables. Practical implementations of this algorithm incorporate statistical tests for conditional independence, in place of a CI oracle. In this paper, we analyze the sample complexity of causal discovery algorithms without a CI oracle: given a certain level of confidence, how many data points are needed for a causal discovery algorithm to identify a causal structure? Furthermore, our methods allow us to quantify the value of domain expertise in terms of data samples. Finally, we demonstrate the accuracy of these sample rates with numerical examples, and quantify the benefits of sparsity priors and known causal directions.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 6 of its 27 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

6 of 27 references.

References · 6

  1. 2013Causal Inference and Causal Explanation with Background Knowledgecited by 168
  2. 2018Learning and Testing Causal Models with Interventionscited by 29
  3. 2017Testing Conditional Independence of Discrete Distributionscited by 22
  4. 2018Causal Inference via Kernel Deviance Measurescited by 22
  5. 2013An Algorithm for Deciding if a Set of Observed Independencies Has a Causal Explanationcited by 17
  6. 2019Testing Conditional Independence on Discrete Data using Stochastic Complexitycited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 2; 2026: 1.

9 papers.

  1. 2022Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalizationcited by 12
  2. 2024Identifiability Guarantees for Causal Disentanglement from Purely Observational Datacited by 7
  3. 2023Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learningcited by 5
  4. 2023On sample complexity of conditional independence testing with Von Mises estimator with application to causal discoverycited by 4
  5. 2024Probably approximately correct high-dimensional causal effect estimation given a valid adjustment setcited by 2
  6. 2024Learning Dynamic Bayesian Networks from Data: Foundations, First Principles and Numerical Comparisonscited by 0
  7. 2025Sample Complexity of Nonparametric Closeness Testing for Continuous Distributions and Its Application to Causal Discovery with Hidden Confoundingcited by 0
  8. 2025Probably Approximately Correct Causal Discoverycited by 0
  9. 2026Causal Preference Elicitationcited by 0