Double-NN combines extended fiducial inference with deep neural networks to produce individual treatment effect prediction intervals, with a consistency proof allowing model size O(n^ζ) for ζ<1.
(2019), Optimal approximation with sparsely connected deep neural networks, SIAM Journal on Mathematics of Data Science, 1, 8--45
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
-
Extended Fiducial Inference for Individual Treatment Effects via Deep Neural Networks
Double-NN combines extended fiducial inference with deep neural networks to produce individual treatment effect prediction intervals, with a consistency proof allowing model size O(n^ζ) for ζ<1.