mlsanityData to 7 Oct 2026

ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity

arXiv 2603.07319 ↗First posted 7 Mar 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-group learning is a learning task that focuses on controlling predictors' conditional losses over specified subgroups. We propose ShakyPrepend, a method that leverages tools inspired by differential privacy to obtain improved theoretical guarantees over existing approaches. Through numerical experiments, we demonstrate that ShakyPrepend adapts to both group structure and spatial heterogeneity. We provide practical guidance for deploying multi-group learning algorithms in real-world settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 7 Mar 2026.

Builds on

20 of 27 references.

References · 20

  1. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  2. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
  3. 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 215
  4. 2014Preserving Statistical Validity in Adaptive Data Analysiscited by 102
  5. 2015Algorithmic Stability for Adaptive Data Analysiscited by 88
  6. 2019Managing Popularity Bias in Recommender Systems with Personalized Re-rankingcited by 81
  7. 2015Generalization in Adaptive Data Analysis and Holdout Reusecited by 76
  8. 2015The Ladder: A Reliable Leaderboard for Machine Learning Competitionscited by 67
  9. 2020Moment Multicalibration for Uncertainty Estimationcited by 63
  10. 2021Multi-group Agnostic PAC Learnabilitycited by 42
  11. 2023Oracle Efficient Online Multicalibration and Omnipredictioncited by 36
  12. 2023A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learningcited by 29
8 more
  1. 2021Online Minimax Multiobjective Optimization: Multicalibeating and Other Applicationscited by 26
  2. 2021Simple and near-optimal algorithms for hidden stratification and multi-group learningcited by 26
  3. 2024Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Riskscited by 13
  4. 2024Group-wise oracle-efficient algorithms for online multi-group learningcited by 8
  5. 2024Multi-group Learning for Hierarchical Groupscited by 7
  6. 2017Climbing a shaky ladder: Better adaptive risk estimationcited by 6
  7. 2025Panprediction: Optimal Predictions for Any Downstream Task and Losscited by 4
  8. 2024Learning With Multi-Group Guarantees For Clusterable Subpopulationscited by 3

Built on by

Not cited yet.