Causal Structure Learning

By Christina Heinze-Deml, Marloes H. Maathuis, Nicolai Meinshausen. 2017

247 citations recorded by the source corpus.

Graphical models can represent a multivariate distribution in a convenient and accessible form as a graph. Causal models can be viewed as a special class of graphical models that represent not only the distribution of the observed system but also the distributions under external interventions. They hence enable predictions under hypothetical interventions, which is important for decision making. The challenging task of learning causal models from data always relies on some underlying assumptions. We discuss several recently proposed structure learning algorithms and their assumptions, and we compare their empirical performance under various scenarios.

Subfields: Artificial Intelligence, Statistics and Probability, Probabilistic & Bayesian Methods, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

In Probabilistic & Bayesian Methods

In Causal Inference & Discovery

Citations in the corpus

Differentiable Causal Discovery from Interventional Data (2020, background): “In this work, we address the problem of data-driven causal discovery [16].”
An Analysis of the Adaptation Speed of Causal Models (2020, background): “This work has set a fruitful line of research for robust machine learning (Heinze-Deml et al., 2018b,a; Rothenhäusler et al., 2019; Arjovsky et al., 2019).”
Learning Neural Causal Models from Unknown Interventions (2019, background): “Furthermore, most of these approaches either assume full knowledge of the intervention or make strong assumptions about its form (Heinze-Deml et al., 2018).”
Invariant Causal Prediction for Nonlinear Models (2017, background): “independent of B, given C, if and only if Ais d-separated (in G) from B, given C. The concept of d-separation (Pearl, 1985, 1988) is dened in Peters et al. (2017, Def. 6.1), for example. 3. Also see Heinze-Deml et al. (2018) for a review and empirical comparison of recently proposed causal structure”
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures (2021, background): “While Structural Causal Models (SCMs) provide a generative model over the data, they are hard to learn from data due to the non-identiﬁability of the causal models without interventional data [7] and the combinatorial nature of the space of DAGs [15].”
From hype to reality: data science enabling personalized medicine (2018, background): “We refer to [60] for a review paper.”
On causal discovery with an equal-variance assumption (2018, background): “ossible under assumptions such as non-linearity with additive errors, linearity with non-Gaussian errors, and linearity with errors of equal variance; see the reviews of Drton and Maathuis (2017) and Heinze-Deml et al. (2018) or the book of Peters et al. (2017). This note is concerned with the equal”
D’ya Like DAGs? A Survey on Structure Learning and Causal Discovery (2021, background): “, [69, 92, 230]), however, these reviews cover combinatoric approaches to causal discovery, hence why we primarily focus on the recent flurry of developments in continuous optimization approaches.”