Research map / Probabilistic and scientific modeling / Variational and generative sampling
GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes
Valentyn Melnychuk, Stefan Feuerriegel
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use GDR-learner instead of plug-in | CNFs · HC-MNIST (a=1) | median out-sample W2: 0.653 -> 0.572 | Improved |
| use GDR-learner instead of IPTW | CVAEs · HC-MNIST (a=0) | median out-sample W2: 1.327 -> 1.306 | Improved |
| use GDR-learner instead of RA | CNFs · HC-MNIST (a=0) | median out-sample W2: 0.603 -> 0.613 | Hurt |
| use GDR-learner instead of plug-in | CGANs · HC-MNIST (a=0) | median out-sample W2: 1.511 -> 1.909 | Hurt |
| use GDR-learner instead of IPTW | CNFs · ACIC 2016 full setting | log-prob: 47.27% and 50.65% of runs improved | No clear effect |
| use GDR-learner instead of IPTW with restricted linear target model | CNFs · ACIC 2016 linear setting | log-prob: 61.82% and 60.26% of runs improved | Improved |
| use GDR-learner instead of RA | CNFs · ACIC 2016 linear setting | log-prob: 22.34% and 25.45% of runs improved | Hurt |
| increase training set size | GDR-learners · synthetic noisy moons | W2 | Improved |
Closest papers by meaning
- Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding (ICML 2024 · similarity 0.88)
- Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting (NeurIPS 2025 · similarity 0.86)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.86)
- Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks (ICLR 2025 · similarity 0.85)
- On Divergence Measures for Training GFlowNets (NeurIPS 2024 · similarity 0.85)
- Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator (ICML 2025 · similarity 0.85)
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.
