mlsanityData to 7 Oct 2026

Invariant Risk Minimization Is A Total Variation Model

arXiv 2405.01389 ↗First posted 2 May 2024cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Invariant risk minimization (IRM) is an arising approach to generalize invariant features to different environments in machine learning. While most related works focus on new IRM settings or new application scenarios, the mathematical essence of IRM remains to be properly explained. We verify that IRM is essentially a total variation based on L2 norm (TV-ℓ2) of the learning risk with respect to the classifier variable. Moreover, we propose a novel IRM framework based on the TV-ℓ1 model. It not only expands the classes of functions that can be used as the learning risk and the feature extractor, but also has robust performance in denoising and invariant feature preservation based on the coarea formula. We also illustrate some requirements for IRM-TV-ℓ1 to achieve out-of-distribution generalization. Experimental results show that the proposed framework achieves competitive performance in several benchmark machine learning scenarios.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

11 of 24 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2019Invariant Risk Minimizationcited by 1,832
  4. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  5. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  6. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  7. 2020Environment Inference for Invariant Learningcited by 306
  8. 2021Heterogeneous Risk Minimizationcited by 90
  9. 2022ZIN: When and How to Learn Invariance Without Environment Partition?cited by 58
  10. 2020In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustnesscited by 49
  11. 2020Meta-Learning for Few-Shot Land Cover Classificationcited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Out-of-distribution Generalization for Total Variation based Invariant Risk Minimizationcited by 3
  2. 2026Generalizable Multimodal Large Language Model Editing via Invariant Trajectory Learningcited by 1
  3. 2025Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performancecited by 0
  4. 2026Environment-Conditioned Tail Reweighting for Invariant Learning under Mixed Shiftscited by 0
  5. 2026A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systemscited by 0