AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Necessary and sufficient graphical conditions for optimal adjustment sets in causal graphical models with hidden variables

Jakob Runge

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Minimax estimation rates · 3 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
use O-set instead of Adjust-setLinReg adjustment estimator · Linear experiments, optimal configurations, n=100RMSEImproved
use minimized sets Omin or Adjustmin instead of O-set (ablation)LinReg adjustment estimator · Linear experiments, optimal configurationsRMSEHurt
use O-set instead of Adjust-set in non-optimal configurationsLinReg adjustment estimator · Non-optimal configurations (7%)RMSEImproved
use O-set instead of OCmin or AdjustXmin in non-optimal configurationsLinReg adjustment estimator · Non-optimal configurationsRMSEMixed
reduce sample size to n = 30O-set · Linear experiments, small sampleRMSEMixed
use O-set with kNN estimatorkNN regression · Random configurationsrank by variance: 50%Improved
use O-set with MLP estimator at higher cardinalitiesMLP · Optimal configurationsrank by variance: 50%Improved
use O-set with random forest estimatorRandom forest regression · Random configurationsrank by varianceNo clear effect
use O-set with DML estimatorDML partially linear · Linear optimal configurationsrank by varianceImproved

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