A kernel-based causal learning algorithm

By Xiaohai Sun, Dominik Janzing, Bernhard Schölkopf, Kenji Fukumizu. 2007

83 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Management Science and Operations Research

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 Computational Theory and Mathematics

In Management Science and Operations Research

Citations in the corpus

Learning Neural Causal Models from Unknown Interventions (2019, methodology): “Constraint-based methods (Spirtes et al., 2000; Sun et al., 2007; Zhang et al., 2012) infer the DAG by analyzing the conditional independence of data.”
Kernel-based Conditional Independence Test and Application in Causal Discovery (2011, positive): “Sun et al. (2007) and Tillman et al. (2009) pro-pose to use CI PERM for CI testing in PC. Based on the promising results of KCI-test, we propose to also apply it to causal inference.”
A Kernel Test for Three-Variable Interactions (2013, methodology): “A number of algorithms have since extended the basic PC algorithm to arbitrary probability distributions over multivariate random variables [16, 17, 18], by using nonparametric kernel independence tests [19] and conditional dependence tests [20, 18].”
Causal Discovery with Reinforcement Learning (2019, methodology): “Examples include [25, 33] using kernel-based conditional independence criteria and the well-known PC algorithm [24].”
Causal reasoning by evaluating the complexity of conditional densities with kernel methods (2008, methodology): “Due to the disadvantage that our method becomes computationally intractable for many variables we propose to apply conventional constraint-based approaches like the IC-algorithm (as well as a new algorithm using kernel-based independence tests [19]) to obtain partial information on the causal direct”
Causal Inference via Kernel Deviance Measures (2018, methodology): “While methods that attempt to recover the causal structure by analyzing conditional independencies present in the data [20, 23] are mathematically well-founded, they are not robust to the choice of conditional independence testing methodology.”
Kernel Measures of Conditional Dependence (2007, methodology): “Covariance operators on RKHSs have been successfully used for capturing dependence and conditional dependence of random variables, by incorporating high order moments [5, 8, 16].”
Nonlinear directed acyclic structure learning with weakly additive noise models (2009, background): “KCL [11] is a heuristic search for a mixed graph that uses the same kernel-based dependence measures as kPC (while not determining significance threhsholds via a hypothesis test), but does not take advantage of additive noise models.”