AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

The Missing Invariance Principle found -- the Reciprocal Twin of Invariant Risk Minimization

Dongsung Huh, Avinash Baidya

NeurIPS 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 3 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 IRM-v1 with MRI-v1 (PM)invariance penalty · S-T Regression testrisk: 1.00 -> 0.54Improved
replace IRM-v1 with MRI-v1 (ALM)invariance penalty · S-T Regression testrisk: 0.62 -> 0.46Improved
replace IRM-v1 with MRI-v1 (ALM)invariance penalty · S-T Classification testaccuracy: 0.77 -> 0.86Improved
replace IRM-v1 with MRI-v1 (PM)invariance penalty · S-T Classification testaccuracy: 0.52 -> 0.85Improved
replace IRM-v1 with MRI-v1 (ALM)invariance penalty · CMNISTa testrisk: 0.69 -> 0.64Improved
replace IRM-v1 with MRI-v1 (ALM)invariance penalty · CMNISTb testrisk: 0.47 -> 0.29Improved
replace IRM-v1 with MRI-v1 (ALM)invariance penalty · CMNISTa testaccuracy: 0.66 -> 0.65No clear effect
replace IRM-v1 with MRI-v1 (ALM)invariance penalty · CMNISTb testaccuracy: 0.91 -> 0.9No clear effect
add invariance constraint (IRM-v1 PM) over ERMERM · CMNISTa testaccuracy: 0.10 -> 0.23Mixed
use MRI-v1 instead of ERMERM · S-T Classification testaccuracy: 0.50 -> 0.86Improved
switch penalty method (PM) to augmented Lagrangian (ALM) (ablation)IRM-v1 · S-T Classification testaccuracy: 0.52 -> 0.77Improved
switch penalty method (PM) to augmented Lagrangian (ALM) (ablation)MRI-v1 · CMNISTb testrisk: 0.4 -> 0.29Improved

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