Optimal Structure Identification With Greedy Search

By David Maxwell Chickering. 2002

2,270 citations recorded by the source corpus.

How researchers see this paper

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

In Optimization & Training

Citations in the corpus

Bayesian Structure Learning with Generative Flow Networks (2022, methodology): “While DAG-GFlownet operates on the space of DAGs directly, the structure of the GFlowNet may eventually be adapted to work with alternative representations of statistical dependencies in Bayesian networks, such as essential graphs for MECs (Chickering, 2002).”
Differentiable Causal Discovery from Interventional Data (2020, background): “This problem presents two main challenges: 1) the size of the search space is super-exponential in the number of nodes [5] and 2) the true DAG is not always identifiable (more severe without interventional data).”
An Analysis of the Adaptation Speed of Causal Models (2020, methodology): “, 2000) or score-based methods using greedy search (Chickering, 2002) or more recently continuous optimization (Zheng et al.”
Gradient-Based Neural DAG Learning (2019, methodology): “Most score-based methods embrace the combinatorial nature of the problem via greedy search procedures [3, 2].”
Learning Neural Causal Models from Unknown Interventions (2019, methodology): “Score-based methods search through the space of all possible directed acyclic graphs (DAGs) representing the causal structure based on some form of scoring function for network structures [9, 22, 23, 24, 25, 26, 27].”
Causal Discovery from Heterogeneous/Nonstationary Data (2019, background): “The so-called score-based approach (see, e.g., (Chickering, 2003; Heckerman et al., 1995)) searches for the equivalence class which gives the highest score under some scoring criteria, such as the Bayesian Information Criterion (BIC), the posterior of the graph given the data (Heckerman et al.,…”
Learning stable and predictive structures in kinetic systems (2018, neutral): “[2015], Donoho [2006], Candès [2006] on these estimated derivatives ̂̇ Y (i) t` = d ∑”
Causal Generative Neural Networks (2017, methodology): “, 2000], the score-based methods GES [Chickering, 2002], LiNGAM [Shimizu et al.”
Causal inference by using invariant prediction: identification and confidence intervals (2015, methodology): “For known intervention targets, Cooper and Yoo (1999) incorporated the intervention effects as mechanism changes (Tian and Pearl, 2001) into a Bayesian framework and Hauser and Bühlmann (2015) modified the greedy equivalence search (Chickering, 2002) for perfect interventions.”
Learning generative models for protein fold families (2011, background): “Broadly, the previously considered approaches to this problem are either constraint-based [30, 29] or score-based [8].”
CAM: Causal Additive Models, high-dimensional order search and penalized regression (2013, methodology): “GES is used with a linear Gaussian score function.”
DAGs with NO TEARS: Continuous Optimization for Structure Learning (2018, methodology): “…on approximate algorithms based on order search (Teyssier and Koller, 2005; Schmidt et al., 2007; Scanagatta et al., 2015, 2016), greedy search (Heckerman et al., 1995; Chickering, 2003; Ramsey et al., 2016), and coordinate descent (Fu and Zhou, 2013; Aragam and Zhou, 2015; Gu et al., 2018).”
Estimating High-Dimensional Directed Acyclic Graphs with the PC-Algorithm (2005, methodology): “The greedy DAG search can be improved by exploiting probabilistic equivalence relations, and the search space can be reduced from individual DAGs to equivalence classes, as proposed in GES (Greedy Equivalent Search, see Chickering, 2002a). Although this method seems quite promising when having few o”
Identifiability of Gaussian structural equation models with equal error variances (2012, methodology): “, 2000] and greedy equivalence search [Chickering, 2002].”
Characterization and greedy learning of interventional Markov equivalence classes of directed acyclic graphs (2011, methodology): “Based on our characterization of interventional essential graphs, we derive a generalization of the GES algorithm of Chickering (2002) aimed at structure learning from interventional data, yielding an algorithm called greedy interventional equivalence search (GIES) which can be used for regularized ”
Causal Discovery with Reinforcement Learning (2019, methodology): “While there have been well-defined score functions such as the Bayesian Information Criterion (BIC) or Minimum Description Length (MDL) score (Schwarz, 1978; Chickering, 2002) and the Bayesian Gaussian equivalent (BGe) score (Geiger and Heckerman, 1994) for linear-Gaussian models, Problem (1) is gen”
Structural Intervention Distance (SID) for Evaluating Causal Graphs (2013, methodology): “, 2006), greedy equivalent search (GES) (Chickering, 2002) and greedy DAG search based on the assumption of equal error variances (GDSEEV) (Peters and Bühlmann, 2014).”