In prediction-intervention games, stable-blanket predictors are at least as good as causal-parent predictors for two classes of follower objectives and can be worst-case optimal under additional conditions.
Instead of modeling a follower optimizing its own utility, the deployment-induced shift inXis encoded directly in the structural assignments of the SCM
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prediction-Intervention Games and Invariant Sets
In prediction-intervention games, stable-blanket predictors are at least as good as causal-parent predictors for two classes of follower objectives and can be worst-case optimal under additional conditions.