AI Paper Atlas

Research map / Image generation / Super-resolution

The Conditional Super Learner

Gilmer Valdés, Yannet Interian, Efstathios D. Gennatas, Mark J. van der Laan

TPAMI 2021 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 8 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
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 -0.125Mixed
replace linear stacking with CSL (neural-net oracle)expert library · PMLB regression (19 datasets)R2: 11 better, 8 same, 1 worseImproved
use CSL instead of random foresthierarchical synthetic data · 564_fried (synthetic)R2: 0.82 -> 0.97Improved
use CSL instead of gradient boostinghierarchical synthetic data · 574_house_16H (synthetic)R2: 0.93 -> 0.98Improved
use CSL instead of best base experthierarchical synthetic data · 564_fried (synthetic)R2: 0.45 -> 0.97Improved
partition space with CSL oracle into 3 regions with depth-5 treessingle depth-5 tree · NYC house rental pricesR2: 0.62 -> 0.68Improved
use random forest instead of CSLinterpretable CSL · NYC house rental pricesR2: 0.68 -> 0.72Improved
mix trees with linear experts in the library (ablation)CSL · hierarchical synthetic dataoptimizationHurt

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