GANICE uses an extended Wasserstein distance and cellwise critic in a GAN to estimate conditional interventional distributions with minimax optimality guarantees.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.ST 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The general regularization scheme is extended to conditional density estimation, yielding a new estimator with proven convergence rates that matches or beats the Nadaraya-Watson estimator in experiments.
citing papers explorer
-
Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
GANICE uses an extended Wasserstein distance and cellwise critic in a GAN to estimate conditional interventional distributions with minimax optimality guarantees.
-
The general regularisation scheme applied to conditional density estimation
The general regularization scheme is extended to conditional density estimation, yielding a new estimator with proven convergence rates that matches or beats the Nadaraya-Watson estimator in experiments.