mlsanityData to 7 Oct 2026

Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks

arXiv 2507.04033 ↗First posted 5 Jul 2025cs.LG cs.CY math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in recent years, and yet there is no standard, widely accepted method for the constrained training of DNNs. In this paper, we provide a challenging benchmark of real-world large-scale fairness-constrained learning tasks, built on top of the US Census (Folktables). We point out the theoretical challenges of such tasks and review the main approaches in stochastic approximation algorithms. Finally, we demonstrate the use of the benchmark by implementing and comparing three recently proposed, but as-of-yet unimplemented, algorithms both in terms of optimization performance, and fairness improvement. We release the code of the benchmark as a Python package at https://github.com/humancompatible/train.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

40 of 57 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  4. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  5. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  6. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
  7. 2015Censoring Representations with an Adversarycited by 191
  8. 2021A survey on datasets for fairness-aware machine learningcited by 157
  9. 2018Stochastic subgradient method converges on tame functionscited by 120
  10. 2018Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goalscited by 103
  11. 2020Training robust neural networks using Lipschitz boundscited by 98
  12. 2021Fairness via Representation Neutralizationcited by 63
28 more
  1. 2021Fairness in Rankings and Recommendations: An Overviewcited by 62
  2. 2022Fairness Testing: A Comprehensive Survey and Analysis of Trendscited by 61
  3. 2016Learning to Pivot with Adversarial Networkscited by 55
  4. 2022Algorithmic Fairness Datasets: the Story so Farcited by 51
  5. 2021Constrained Learning with Non-Convex Lossescited by 42
  6. 2023FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methodscited by 33
  7. 2020Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimizationcited by 30
  8. 2021An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangianscited by 25
  9. 2021A Stochastic Sequential Quadratic Optimization Algorithm for Nonlinear Equality Constrained Optimization with Rank-Deficient Jacobianscited by 21
  10. 2022Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problemscited by 21
  11. 2021Worst-Case Complexity of an SQP Method for Nonlinear Equality Constrained Stochastic Optimizationcited by 19
  12. 2019Unbiased Multilevel Monte Carlo: Stochastic Optimization, Steady-state Simulation, Quantiles, and Other Applicationscited by 17
  13. 2019Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairnesscited by 16
  14. 2021Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programmingcited by 16
  15. 2024OxonFair: A Flexible Toolkit for Algorithmic Fairnesscited by 12
  16. 2023Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimizationcited by 11
  17. 2023Sequential Quadratic Optimization for Stochastic Optimization with Deterministic Nonlinear Inequality and Equality Constraintscited by 10
  18. 2025Cooper: A Library for Constrained Optimization in Deep Learningcited by 10
  19. 2024ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methodscited by 8
  20. 2021Constrained Optimization in the Presence of Noisecited by 7
  21. 2023fairret: a Framework for Differentiable Fairness Regularization Termscited by 7
  22. 2017Ghost Penalties in Nonconvex Constrained Optimization: Diminishing Stepsizes and Iteration Complexitycited by 6
  23. 2023An Adaptive Sampling Augmented Lagrangian Method for Stochastic Optimization with Deterministic Constraintscited by 5
  24. 2025Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraintscited by 5
  25. 2022Fairness in Forecasting of Observations of Linear Dynamical Systemscited by 4
  26. 2025Position: Adopt Constraints Over Fixed Penalties in Deep Learningcited by 4
  27. 2021Subgroup Fairness in Two-Sided Marketscited by 3
  28. 2023Stochastic Approximation for Expectation Objective and Expectation Inequality-Constrained Nonconvex Optimizationcited by 2

Built on by

Not cited yet.