AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Is Spurious Correlation Removal Always Learnable?

Yibo Zhou, Bo Li, Hai-Miao Hu, Hanzi Wang, Xiaokang Zhang, Ruifan Zhang

ICML 2026 · Learning theory and algorithms › Sample complexity · approach: Learning halfspaces under noise · 0 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
increase environment diversity gamma from 0.1 to 0.6 (ablation)exhaustive/invariance feature selection · Synthetic (d=20,k=4)feature selection accuracy: .20 -> 1.0 (+.80)Improved
increase samples per environment from 200 to 2000 (ablation)feature selection · Syntheticfeature selection accuracy: .70 -> 1.0 (+.30)Improved
reduce invariant dimension k from 8 to 3 (ablation)feature selection · Syntheticfeature selection accuracy: .73 -> 1.0 (+.27)Improved
increase SNR from 1 to 10 (ablation)feature selection · Syntheticfeature selection accuracy: .75 -> .93 (+.18)Improved
increase training size from N=500 to N=2000 (IRM gap to oracle)IRM · ColoredMNIST (gamma=0.4)gap vs oracle: 0.100 -> 0.020Improved
increase diversity from low to high (ablation)IRM · CMNISTworst-group accuracy: .61 -> .84Improved
increase diversity from low to high (ablation)ERM · CMNISTworst-group accuracy: .54 -> .76Improved
reduce shared spurious bias (high diversity) (ablation)GDRO · CelebAworst-group accuracy: .85 -> .91Improved
reduce shared spurious bias (high diversity) (ablation)GDRO · Waterbirdsworst-group accuracy: .79 -> .87Improved
use group-aware GDRO instead of IRM at low diversityGDRO · CelebAworst-group accuracy: IRM .82 vs GDRO .85Improved
use IRM instead of ERM at low diversityIRM · ColoredMNISTworst-group accuracy: ERM .54 vs IRM .61Improved
use IRM instead of ERM at low diversityIRM · CelebAoverall accuracy: .90 vs .89No clear effect

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