Develops an adversary-free counterfactual prediction framework by deriving a variational objective that upper-bounds mutual information between stochastic representations and treatments.
Sepp Hochreiter and J¨ urgen Schmidhuber
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adversary-Free Counterfactual Prediction via Information-Regularized Representations
Develops an adversary-free counterfactual prediction framework by deriving a variational objective that upper-bounds mutual information between stochastic representations and treatments.