Introduces OR-learners that can strictly improve estimation error of standard Neyman-orthogonal learners under the low-dimensional manifold hypothesis, while showing that balancing constraints require additional inductive bias.
Johansson, Uri Shalit, and David Son- tag
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
-
Orthogonal Representation Learning for Estimating Causal Quantities
Introduces OR-learners that can strictly improve estimation error of standard Neyman-orthogonal learners under the low-dimensional manifold hypothesis, while showing that balancing constraints require additional inductive bias.