mlsanityData to 14 Oct 2026

Stochastic Differentially Private and Fair Learning

arXiv 2210.08781 ↗First posted 17 Oct 2022cs.LG cs.CRcited by 16

Not on the map. Why?

Abstract (arXiv)

Machine learning models are increasingly used in high-stakes decision-making systems. In such applications, a major concern is that these models sometimes discriminate against certain demographic groups such as individuals with certain race, gender, or age. Another major concern in these applications is the violation of the privacy of users. While fair learning algorithms have been developed to mitigate discrimination issues, these algorithms can still leak sensitive information, such as individuals' health or financial records. Utilizing the notion of differential privacy (DP), prior works aimed at developing learning algorithms that are both private and fair. However, existing algorithms for DP fair learning are either not guaranteed to converge or require full batch of data in each iteration of the algorithm to converge. In this paper, we provide the first stochastic differentially private algorithm for fair learning that is guaranteed to converge. Here, the term "stochastic" refers to the fact that our proposed algorithm converges even when minibatches of data are used at each iteration (i.e. stochastic optimization). Our framework is flexible enough to permit different fairness notions, including demographic parity and equalized odds. In addition, our algorithm can be applied to non-binary classification tasks with multiple (non-binary) sensitive attributes. As a byproduct of our convergence analysis, we provide the first utility guarantee for a DP algorithm for solving nonconvex-strongly concave min-max problems. Our numerical experiments show that the proposed algorithm consistently offers significant performance gains over the state-of-the-art baselines, and can be applied to larger scale problems with non-binary target/sensitive attributes.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 43 of its 82 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

43 of 82 references.

References · 43

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2020Extracting Training Data from Large Language Modelscited by 2,189
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  6. 2014Certifying and removing disparate impactcited by 715
  7. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  8. 2018A Reductions Approach to Fair Classificationcited by 587
  9. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 552
  10. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  11. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  12. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
31 more
  1. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  2. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 270
  3. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  4. 2019Private Stochastic Convex Optimization with Optimal Ratescited by 186
  5. 2019Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methodscited by 148
  6. 2018Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcited by 128
  7. 2013Discrimination in Online Ad Deliverycited by 93
  8. 2014Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discriminationcited by 83
  9. 2021Private Stochastic Convex Optimization: Optimal Rates in ℓ1 Geometrycited by 83
  10. 2018Differentially Private Fair Learningcited by 76
  11. 2016A Confidence-Based Approach for Balancing Fairness and Accuracycited by 73
  12. 2017Efficient Private ERM for Smooth Objectivescited by 61
  13. 2017Non-convex Finite-Sum Optimization Via SCSG Methodscited by 61
  14. 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
  15. 2020Fair Learning with Private Demographic Datacited by 46
  16. 2018Blind Justice: Fairness with Encrypted Sensitive Attributescited by 41
  17. 2020Efficient Search of First-Order Nash Equilibria in Nonconvex-Concave Smooth Min-Max Problemscited by 39
  18. 2019Toward a better trade-off between performance and fairness with kernel-based distribution matchingcited by 36
  19. 2019Equal Opportunity in Online Classification with Partial Feedbackcited by 35
  20. 2019R'enyi Fair Inferencecited by 33
  21. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  22. 2022Faster Rates of Convergence to Stationary Points in Differentially Private Optimizationcited by 32
  23. 2019An accelerated inexact proximal point method for solving nonconvex-concave min-max problemscited by 30
  24. 2019Efficient Privacy-Preserving Stochastic Nonconvex Optimizationcited by 27
  25. 2021A Stochastic Optimization Framework for Fair Risk Minimizationcited by 26
  26. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  27. 2022Differentially Private SGDA for Minimax Problemscited by 23
  28. 2022Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimizationcited by 22
  29. 2020Differentially Private and Fair Classification via Calibrated Functional Mechanismcited by 20
  30. 2021Optimal Algorithms for Differentially Private Stochastic Monotone Variational Inequalities and Saddle-Point Problemscited by 17
  31. 2022SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensemblescited by 8

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 6; 2025: 5.

16 papers.

Sort:

  1. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  2. 2024How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimizationcited by 10
  3. 2023Optimal Differentially Private Model Training with Public Datacited by 9
  4. 2024Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Lossescited by 8
  5. 2024Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problemscited by 7
  6. 2023FairDP: Certified Fairness with Differential Privacycited by 4
  7. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  8. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4
  9. 2024Differentially Private Fair Binary Classificationscited by 3
  10. 2024PFGuard: A Generative Framework with Privacy and Fairness Safeguardscited by 3
  11. 2024Combining Machine Learning Defenses without Conflictscited by 2
  12. 2025Learning with Differentially Private (Sliced) Wasserstein Gradientscited by 2
4 more
  1. 2025Private Rate-Constrained Optimization with Applications to Fair Learningcited by 1
  2. 2025Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classificationcited by 1
  3. 2025On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learningcited by 0
  4. 2025FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utilitycited by 0