Debiased Machine Learning without Sample-Splitting for Stable Estimators

Authors: Qizhao Chen, Vasilis Syrgkanis, Morgane Austern

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experimental Evaluation We consider a synthetic experimental evaluation of our main theoretical findings. We focus on the partially linear model with a scalar outcome Y 2 R, a scalar continuous treatment T 2 R and many controls X 2 Rnx, where: T = p0(X) + , N(0, 1), Y = 0T + f0(X) + , N(0, 1).
Researcher Affiliation Academia Qizhao Chen Harvard University Cambridge, MA 02138 qizhaochen@g.harvard.edu Vasilis Syrgkanis Stanford University Stanford, CA 94305 vsyrgk@stanford.edu Morgane Austern Harvard University Cambridge, MA 02138 morgane.austern@gmail.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the described methodology.
Open Datasets No We consider a synthetic experimental evaluation of our main theoretical findings. We focus on the partially linear model with a scalar outcome Y 2 R, a scalar continuous treatment T 2 R and many controls X 2 Rnx, where: T = p0(X) + , N(0, 1), Y = 0T + f0(X) + , N(0, 1).
Dataset Splits No For the cross-fitted estimates we used 2 splits.
Hardware Specification No The paper does not provide any specific hardware details used for running its experiments.
Software Dependencies No The paper mentions machine learning models like 1-nearest neighbor and random forest regression, but does not provide specific software names with version numbers.
Experiment Setup No The paper mentions using sub-sampled 1-nearest neighbor and random forest regression with sub-sample sizes based on theoretical specifications (e.g., m = n0.49), but it does not provide comprehensive experimental setup details like specific hyperparameters (learning rates, batch sizes), optimizer settings, or model initialization details.