AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Minimax-Optimal Aggregation for Density Ratio Estimation

Lukas Gruber, Markus Holzleitner, Sepp Hochreiter, Werner Zellinger

ICLR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing

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
aggregate models instead of cross-validation selectionKuLSIF · Geometric datasets (avg)Bregman error: 11.205 -> 10.683Improved
aggregate models instead of cross-validation selectionExp · Geometric datasets (avg)Bregman error: 13.392 -> 11.529Improved
aggregate DeepLR models instead of CV-selected DeepLR (Ablation 1) (ablation)DeepLR · Geometric c3,d1.70Bregman error: 7.280 -> 6.504Improved
tune KMM bandwidth by aggregation instead of median heuristic (Ablation 2) (ablation)KMM · Geometric c3,d1.70Bregman error: 16.783 -> 13.223Improved
use minimax aggregation instead of model averaging (Ablation 3) (ablation)KuLSIF · Geometric c3,d1.70Bregman error: 8.553 -> 8.320Improved
use aggregation instead of Super Learner (ablation)KuLSIF · Geometric datasets (avg)Bregman error: 11.009 -> 10.683Improved
use aggregation instead of Bayesian model averaging (ablation)Exp · Geometric datasets (avg)Bregman error: 12.972 -> 11.529Improved
aggregate instead of cross-validationKuLSIF · MiniDomainNettarget accuracy: 0.528 -> 0.535Improved
aggregate instead of cross-validationKuLSIF · HHARtarget accuracy: 0.737 -> 0.780Improved
aggregate instead of cross-validationLR · Amazon Reviewstarget accuracy: 0.785 -> 0.789Improved
increase number of models with suboptimal hyperparameters (Ablation 4) (ablation)Aggregation · KuLSIF geometricerrorNo clear effect
increase data dimensionality (Ablation 5) (ablation)Cross-validation · Gaussian mixtureserrorHurt

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