mlsanityData to 7 Oct 2026

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

arXiv 2310.18593 ↗First posted 28 Oct 2023stat.ML cs.CY cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Fair Principal Component Analysis (PCA) is a problem setting where we aim to perform PCA while making the resulting representation fair in that the projected distributions, conditional on the sensitive attributes, match one another. However, existing approaches to fair PCA have two main problems: theoretically, there has been no statistical foundation of fair PCA in terms of learnability; practically, limited memory prevents us from using existing approaches, as they explicitly rely on full access to the entire data. On the theoretical side, we rigorously formulate fair PCA using a new notion called probably approximately fair and optimal (PAFO) learnability. On the practical side, motivated by recent advances in streaming algorithms for addressing memory limitation, we propose a new setting called fair streaming PCA along with a memory-efficient algorithm, fair noisy power method (FNPM). We then provide its it statistical guarantee in terms of PAFO-learnability, which is the first of its kind in fair PCA literature. Lastly, we verify the efficacy and memory efficiency of our algorithm on real-world datasets.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 45 of its 86 references that are in the map. First posted on arXiv 28 Oct 2023.

Builds on

45 of 86 references.

References · 45

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  4. 2014Certifying and removing disparate impactcited by 715
  5. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  6. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  7. 2015An Introduction to Matrix Concentration Inequalitiescited by 391
  8. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  9. 2018Fair Clustering Through Fairletscited by 176
  10. 2019A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Normcited by 105
  11. 2020FairBatch: Batch Selection for Model Fairnesscited by 99
  12. 2022Linear Adversarial Concept Erasurecited by 98
33 more
  1. 2019Guarantees for Spectral Clustering with Fairness Constraintscited by 72
  2. 2018The Price of Fair PCA: One Extra Dimensioncited by 67
  3. 2017Sub-sampled Cubic Regularization for Non-convex Optimizationcited by 63
  4. 2018Online Learning with an Unknown Fairness Metriccited by 61
  5. 2013The Noisy Power Method: A Meta Algorithm with Applicationscited by 58
  6. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  7. 2020Probably Approximately Correct Constrained Learningcited by 47
  8. 2022Kernelized Concept Erasurecited by 47
  9. 2021Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Featurescited by 45
  10. 2020Algorithmic Fairness in Educationcited by 44
  11. 2020Metric-Free Individual Fairness in Online Learningcited by 30
  12. 2016Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithmcited by 29
  13. 2016An Improved Gap-Dependency Analysis of the Noisy Power Methodcited by 24
  14. 2020Fairness in Streaming Submodular Maximization: Algorithms and Hardnesscited by 23
  15. 2023Efficient fair PCA for fair representation learningcited by 23
  16. 2013Memory Limited, Streaming PCAcited by 21
  17. 2021Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updatescited by 21
  18. 2015Fast Differentially Private Matrix Factorizationcited by 20
  19. 2018Convex Formulations for Fair Principal Component Analysiscited by 20
  20. 2019Efficient Fair Principal Component Analysiscited by 20
  21. 2018Streaming PCA and Subspace Tracking: The Missing Data Casecited by 18
  22. 2021Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifoldcited by 18
  23. 2022Scalable Spectral Clustering with Group Fairness Constraintscited by 16
  24. 2018Streaming Kernel PCA with tildeO(√n) Random Featurescited by 11
  25. 2021On the Optimality of the Oja's Algorithm for Online PCAcited by 11
  26. 2018History PCA: A New Algorithm for Streaming PCAcited by 9
  27. 2022Distributionally Robust Fair Principal Components via Geodesic Descentscited by 9
  28. 2023Streaming PCA for Markovian Datacited by 9
  29. 2015Streaming Kernel Principal Component Analysiscited by 8
  30. 2019Robust Streaming PCAcited by 6
  31. 2022Streaming Algorithms for Diversity Maximization with Fairness Constraintscited by 3
  32. 2023Do PAC-Learners Learn the Marginal Distribution?cited by 3
  33. 2014Streaming, Memory Limited Algorithms for Community Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2024Black-Box k-to-1-PCA Reductions: Theory and Applicationscited by 7
  2. 2025Hidden Convexity of Fair PCA and Fast Solver via Eigenvalue Optimizationcited by 1
  3. 2025Achieving Fair PCA Using Joint Eigenvalue Decompositioncited by 0
  4. 2025Detecting Domain Shifts in Myoelectric Activations: Challenges and Opportunities in Stream Learningcited by 0
  5. 2025Implicitly Normalized Online PCA: A Regularized Algorithm with Exact High-Dimensional Dynamicscited by 0