mlsanityData to 14 Oct 2026

Simple and near-optimal algorithms for hidden stratification and multi-group learning

arXiv 2112.12181 ↗First posted 22 Dec 2021cs.LG stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. This paper studies the structure of solutions to the multi-group learning problem, and provides simple and near-optimal algorithms for the learning problem.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 26 of its 58 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

26 of 58 references.

References · 26

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  3. 2018A Reductions Approach to Fair Classificationcited by 587
  4. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
  5. 2019Agnostic Federated Learningcited by 456
  6. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  7. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  8. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  9. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 222
  10. 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 216
  11. 2020No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problemscited by 209
  12. 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 183
14 more
  1. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  2. 2014A Second-order Bound with Excess Lossescited by 95
  3. 2013Data-Driven Robust Optimizationcited by 85
  4. 2020Outcome Indistinguishabilitycited by 75
  5. 2018Marginal Singularity, and the Benefits of Labels in Covariate-Shiftcited by 65
  6. 2018Online Learning with an Unknown Fairness Metriccited by 62
  7. 2020Distributionally Robust Losses for Latent Covariate Mixturescited by 58
  8. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 49
  9. 2021Multi-group Agnostic PAC Learnabilitycited by 44
  10. 2019Advancing subgroup fairness via sleeping expertscited by 30
  11. 2021Realizable Learning is All You Needcited by 25
  12. 2021Multiaccurate Proxies for Downstream Fairnesscited by 17
  13. 2013Relative Deviation Learning Bounds and Generalization with Unbounded Loss Functionscited by 15
  14. 2019An adaptive nearest neighbor rule for classificationcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 7; 2024: 5; 2025: 2; 2026: 9.

28 papers.

Sort:

By area:

  1. 2022Low-Degree Multicalibrationcited by 45
  2. 2022On-Demand Sampling: Learning Optimally from Multiple Distributionscited by 39
  3. 2023A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learningcited by 30
  4. 2022Why does Throwing Away Data Improve Worst-Group Error?cited by 22
  5. 2022An Algorithmic Framework for Bias Bountiescited by 21
  6. 2024Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Riskscited by 14
  7. 2023Optimal Multi-Distribution Learningcited by 13
  8. 2023The sample complexity of multi-distribution learningcited by 12
  9. 2024Group-wise oracle-efficient algorithms for online multi-group learningcited by 9
  10. 2022Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classescited by 8
  11. 2024Multi-group Learning for Hierarchical Groupscited by 8
  12. 2023Agnostic Multi-Group Active Learningcited by 7
16 more
  1. 2024Derandomizing Multi-Distribution Learningcited by 5
  2. 2025Panprediction: Optimal Predictions for Any Downstream Task and Losscited by 4
  3. 2026Group-realizable multi-group learning by minimizing empirical riskcited by 3
  4. 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-playcited by 2
  5. 2023Agnostic Multi-Robust Learning Using ERMcited by 2
  6. 2023Group conditional validity via multi-group learningcited by 1
  7. 2024Diversified Ensembling: An Experiment in Crowdsourced Machine Learningcited by 1
  8. 2025Sample-Adaptivity Tradeoff in On-Demand Samplingcited by 1
  9. 2026The price of multi-group transductive learningcited by 1
  10. 2026Locally Adaptive Multi-Objective Learningcited by 0
  11. 2026Federated Measurement of Demographic Disparities from Quantile Sketchescited by 0
  12. 2026ShakyPrepend: A Multi-Group Learner with Improved Sample Complexitycited by 0
  13. 2026A One-Inclusion Graph Approach to Multi-Group Learningcited by 0
  14. 2026Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imagingcited by 0
  15. 2026Groupwise Distortion Guarantees for Preference-Based Alignmentcited by 0
  16. 2026Sample-Optimal Multi-Group Learning with an ERM Oraclecited by 0