mlsanityData to 7 Oct 2026

Responsible AI (RAI) Games and Ensembles

arXiv 2310.18832 ↗First posted 28 Oct 2023cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Several recent works have studied the societal effects of AI; these include issues such as fairness, robustness, and safety. In many of these objectives, a learner seeks to minimize its worst-case loss over a set of predefined distributions (known as uncertainty sets), with usual examples being perturbed versions of the empirical distribution. In other words, aforementioned problems can be written as min-max problems over these uncertainty sets. In this work, we provide a general framework for studying these problems, which we refer to as Responsible AI (RAI) games. We provide two classes of algorithms for solving these games: (a) game-play based algorithms, and (b) greedy stagewise estimation algorithms. The former class is motivated by online learning and game theory, whereas the latter class is motivated by the classical statistical literature on boosting, and regression. We empirically demonstrate the applicability and competitive performance of our techniques for solving several RAI problems, particularly around subpopulation shift.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 47 of its 94 references that are in the map. First posted on arXiv 28 Oct 2023.

Builds on

47 of 94 references.

References · 47

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2016Wide Residual Networkscited by 3,057
  3. 2021Convex optimizationcited by 2,479
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  9. 2017Counterfactual Fairnesscited by 802
  10. 2019Introduction to Online Convex Optimizationcited by 793
  11. 2020Long-tail learning via logit adjustmentcited by 605
  12. 2019Agnostic Federated Learningcited by 451
35 more
  1. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  2. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  3. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  4. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  5. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  6. 2020Fairness in Machine Learningcited by 194
  7. 2016Distributionally Robust Stochastic Optimization with Wasserstein Distancecited by 182
  8. 2016Variance-based regularization with convex objectivescited by 153
  9. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  10. 2018The Frontiers of Fairness in Machine Learningcited by 139
  11. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  12. 2015Distributionally Robust Logistic Regressioncited by 124
  13. 2018Invariance, Causality and Robustnesscited by 123
  14. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  15. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  16. 2019Distributionally Robust Optimization and Generalization in Kernel Methodscited by 73
  17. 2021DORO: Distributional and Outlier Robust Optimizationcited by 54
  18. 2020FR-Train: A Mutual Information-Based Approach to Fair and Robust Trainingcited by 52
  19. 2015Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithmcited by 50
  20. 2020An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectivescited by 42
  21. 2021Non-convex Distributionally Robust Optimization: Non-asymptotic Analysiscited by 39
  22. 2020Ensuring Fairness Beyond the Training Datacited by 35
  23. 2020Second Order PAC-Bayesian Bounds for the Weighted Majority Votecited by 34
  24. 2018Taking Advantage of Multitask Learning for Fair Classificationcited by 24
  25. 2021Mixed Nash Equilibria in the Adversarial Examples Gamecited by 22
  26. 2013New Analysis and Results for the Frank-Wolfe Methodcited by 17
  27. 2022Holistic Robust Data-Driven Decisionscited by 17
  28. 2021Boosted CVaR Classificationcited by 12
  29. 2022Building Robust Ensembles via Margin Boostingcited by 8
  30. 2022Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Gamescited by 8
  31. 2020Kernel Distributionally Robust Optimizationcited by 6
  32. 2023Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimizationcited by 6
  33. 2022Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networkscited by 3
  34. 2020Learning Minimax Estimators via Online Learningcited by 2
  35. 2022Metric-Fair Classifier Derandomizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Hybrid Responsible AI-Stochastic Approach for SLA Compliance in Multivendor 6G Networkscited by 0