AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Fast Instrument Learning with Faster Rates

Ziyu Wang, Yuhao Zhou, Jun Zhu

NeurIPS 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace RBF-kernel first stage with learned DNN instrument features (ablation)Kernelized IV · f0~GP, D=100, n1=n2=2500Test MSE: .176 -> .035Improved
replace RBF-kernel first stage with learned DNN instrument features (ablation)Kernelized IV · f0~GP, D=100, n1=n2=50090% credible ball coverage: .187 -> .923Improved
replace RBF first stage with learned instruments (ablation)Kernelized IV · f0~GP, D=100, n1=n2=500090% credible ball radius: .156 -> .049Improved
increase sample size n1=n2 from 500 to 5000Proposed · f0~GP, D=100Test MSE: .097 -> .024Improved
increase sample size n1=n2 from 500 to 5000Proposed · f0~GP, D=10090% credible ball coverage: .923 -> .920No clear effect
replace adaptive AGMM-NN/Tree with proposed black-box + kernel methodProposed · predictive, N=2500, D=100runtime (s): 303 -> 25.9Improved
use AGMM-RBF instead of proposedAGMM · predictive, N=2500, D=100runtime (s): 25.9 -> 6.7Mixed
increase dimension D (instruments) for AGMM-Tree and AGMM-NNAGMM-Tree/NN · predictivetest MSEHurt
trained DNN first stage vs RBF kernel or random-init DNN (ablation)Instrument learning · f0~GP, D in {2,40,100}counterfactual MSEImproved
use proposed method vs AGMM-NN and prior MNIST baselineProposed · MNIST/CIFAR image instrumentstest MSEImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy