Under an additive outcome mechanism, the joint interventional effect equals the sum of single-intervention effects minus (K-1) times the observational expectation, so joint interventions are identifiable from single-variable interventions and observational data.
Intervention generalization: A view from factor graph models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models
Under an additive outcome mechanism, the joint interventional effect equals the sum of single-intervention effects minus (K-1) times the observational expectation, so joint interventions are identifiable from single-variable interventions and observational data.