AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability

Jonathan Crabbé, Alicia Curth, Ioana Bica, Mihaela van der Schaar

NeurIPS 2022 · Probabilistic and scientific modeling › Treatment effects · approach: Benchmarking treatment effect models · 6 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
increase predictive scale from 1e-3 to 1all CATE learners · TCGA, Twins, News, ACIC2016correct predictive attributionImproved
increase predictive scaleall CATE learners · TCGA, Twins, News, ACIC2016prognostic misattributionImproved
use S-learner instead of other learnersCATE learner · TCGA, Twins, News, ACIC2016correct predictive attributionHurt
S-learner at low predictive scaleS-learner · low predictive scalePEHEImproved
increase nonlinearity scale from 0 to 1all CATE learners · TCGA, Twins, News, ACIC2016correct predictive attributionHurt
increase nonlinearity scaleall CATE learners · TCGA, Twins, News, ACIC2016prognostic misattributionHurt
increase nonlinearity scale on learner orderingS-learner vs others · nonlinearity experimentrelative rankingNo clear effect
increase propensity scale (treatment assignment bias)CATE learners · Newscorrect predictive attributionHurt
predictive confounding instead of non-confounded propensityCATE learners · Newscorrect predictive attributionHurt
prognostic confounding instead of non-confounded propensityCATE learners · Newscorrect predictive attributionImproved
add balancing regularization (CFRNet vs TARNet) under predictive confounding (ablation)TARNet · Newscorrect predictive attributionHurt
add balancing regularization (CFRNet vs TARNet) under non-predictive confounding (ablation)TARNet · Newscorrect predictive attributionNo clear effect

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