DFIV achieves minimax-optimal rates in Besov spaces for nonparametric IV regression, and beats fixed-feature estimators for spatially inhomogeneous targets.
On deep learning as a remedy for the curse of dimensionality in nonparametric regression
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
-
Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
DFIV achieves minimax-optimal rates in Besov spaces for nonparametric IV regression, and beats fixed-feature estimators for spatially inhomogeneous targets.