Deep IV: A Flexible Approach for Counterfactual Prediction - hartford17a.pdf
proceedings.mlr.press/v70/hartford17a/hartford17a.pdf
1 Users
0 Comments
2 Highlights
0 Notes
Tags
Top Highlights
leverages in- strument variables to train deep networks that directly min- imize the counterfactual prediction error and validate the resulting models on held-out dat
interference
Ready to highlight and find good content?
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.