Research map / Image generation / Super-resolution
The Conditional Super Learner
Gilmer Valdés, Yannet Interian, Efstathios D. Gennatas, Mark J. van der Laan
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 |
|---|---|---|---|
| replace cross-validation single-model selection with CSL (depth-1 tree oracle) | expert library · PMLB regression (84 datasets) | R2: 77.5% of datasets at least same; outlier -0.125 | Mixed |
| replace linear stacking with CSL (neural-net oracle) | expert library · PMLB regression (19 datasets) | R2: 11 better, 8 same, 1 worse | Improved |
| use CSL instead of random forest | hierarchical synthetic data · 564_fried (synthetic) | R2: 0.82 -> 0.97 | Improved |
| use CSL instead of gradient boosting | hierarchical synthetic data · 574_house_16H (synthetic) | R2: 0.93 -> 0.98 | Improved |
| use CSL instead of best base expert | hierarchical synthetic data · 564_fried (synthetic) | R2: 0.45 -> 0.97 | Improved |
| partition space with CSL oracle into 3 regions with depth-5 trees | single depth-5 tree · NYC house rental prices | R2: 0.62 -> 0.68 | Improved |
| use random forest instead of CSL | interpretable CSL · NYC house rental prices | R2: 0.68 -> 0.72 | Improved |
| mix trees with linear experts in the library (ablation) | CSL · hierarchical synthetic data | optimization | Hurt |
Closest papers by meaning
- Structured Prediction for Conditional Meta-Learning (NeurIPS 2020 · similarity 0.84)
- The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning (NeurIPS 2020 · similarity 0.84)
- Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL (ICML 2025 · similarity 0.82)
- SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction (ICLR 2025 · similarity 0.82)
- SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models (NeurIPS 2024 · similarity 0.82)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.82)
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.
