AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes

Valentyn Melnychuk, Stefan Feuerriegel

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 2 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 GDR-learner instead of plug-inCNFs · HC-MNIST (a=1)median out-sample W2: 0.653 -> 0.572Improved
use GDR-learner instead of IPTWCVAEs · HC-MNIST (a=0)median out-sample W2: 1.327 -> 1.306Improved
use GDR-learner instead of RACNFs · HC-MNIST (a=0)median out-sample W2: 0.603 -> 0.613Hurt
use GDR-learner instead of plug-inCGANs · HC-MNIST (a=0)median out-sample W2: 1.511 -> 1.909Hurt
use GDR-learner instead of IPTWCNFs · ACIC 2016 full settinglog-prob: 47.27% and 50.65% of runs improvedNo clear effect
use GDR-learner instead of IPTW with restricted linear target modelCNFs · ACIC 2016 linear settinglog-prob: 61.82% and 60.26% of runs improvedImproved
use GDR-learner instead of RACNFs · ACIC 2016 linear settinglog-prob: 22.34% and 25.45% of runs improvedHurt
increase training set sizeGDR-learners · synthetic noisy moonsW2Improved

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