Eq. (4) gives the causal operator.1.2 The set C represents the smallest set for which Eq. (2) holds. The conditions in Theorem 3.1 allow for full transfer across all intervention functions in This is equivalent to sampling from the mutilated graph. We compute the integrals in Eqs. Finally, we fix the variance in the likelihood of Eq.

This paper studies the problem of learning the correlation structure of a set of intervention functions defined on the directed acyclic graph (DAG) of a causal model. This is useful when we are interested in jointly learning the causal effects of interventions on different subsets of variables in a DAG, which is common in field such as healthcare or operations research. We propose the first multi-task causal Gaussian process (GP) model, which we call DAG-GP, that allows for information sharing across continuous interventions and across experiments on different variables.

Eq. (4) gives the causal operator.1.2 The set C represents the smallest set for which Eq. (2) holds. The conditions in Theorem 3.1 allow for full transfer across all intervention functions in This is equivalent to sampling from the mutilated graph. We compute the integrals in Eqs. Finally, we fix the variance in the likelihood of Eq.

This paper studies the problem of learning the correlation structure of a set of intervention functions defined on the directed acyclic graph (DAG) of a causal model. This is useful when we are interested in jointly learning the causal effects of interventions on different subsets of variables in a DAG, which is common in field such as healthcare or operations research. We propose the first multi-task causal Gaussian process (GP) model, which we call DAG-GP, that allows for information sharing across continuous interventions and across experiments on different variables. We give theoretical results detailing when and how the DAG-GP model can be formulated depending on the DAG. We test both the quality of its predictions and its calibrated uncertainties.