# Optimisation Strategies for Ensuring Fairness in Machine Learning: With and Without Demographics

arXiv: https://arxiv.org/abs/2411.09056 · HTML: https://mlsanity.com/paper/2411.09056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 227 references that are in the map.
- First posted on arXiv 13 Nov 2024.

## Builds on (most cited first, 11 of 11)

- [Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?](https://mlsanity.com/paper/1912.01094/) (2019)
- [A New Approach to Learning Linear Dynamical Systems](https://mlsanity.com/paper/2301.09519/) (2023)
- [On-Line Learning of Linear Dynamical Systems: Exponential Forgetting in Kalman Filters](https://mlsanity.com/paper/1809.05870/) (2018)
- [Beyond Individual and Group Fairness](https://mlsanity.com/paper/2008.09490/) (2020)
- [Computability of Optimizers](https://mlsanity.com/paper/2301.06148/) (2023)
- [Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing](https://mlsanity.com/paper/1910.07870/) (2019)
- [Projection to Fairness in Statistical Learning](https://mlsanity.com/paper/2005.11720/) (2020)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)
- [On the impossibility of non-trivial accuracy under fairness constraints](https://mlsanity.com/paper/2107.06944/) (2021)
- [Quantum open system identification via global optimization: Optimally accurate Markovian models of open systems from time-series data](https://mlsanity.com/paper/2203.17164/) (2022)
- [Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access](https://mlsanity.com/paper/2302.01385/) (2023)

## Abstract (arXiv)

Ensuring fairness has emerged as one of the primary concerns in AI and its related algorithms. Over time, the field of machine learning fairness has evolved to address these issues. This paper provides an extensive overview of this field and introduces two formal frameworks to tackle open questions in machine learning fairness. In one framework, operator-valued optimisation and min-max objectives are employed to address unfairness in time-series problems. This approach showcases state-of-the-art performance on the notorious COMPAS benchmark dataset, demonstrating its effectiveness in real-world scenarios. In the second framework, the challenge of lacking sensitive attributes, such as gender and race, in commonly used datasets is addressed. This issue is particularly pressing because existing algorithms in this field predominantly rely on the availability or estimations of such attributes to assess and mitigate unfairness. Here, a framework for a group-blind bias-repair is introduced, aiming to mitigate bias without relying on sensitive attributes. The efficacy of this approach is showcased through analyses conducted on the Adult Census Income dataset. Additionally, detailed algorithmic analyses for both frameworks are provided, accompanied by convergence guarantees, ensuring the robustness and reliability of the proposed methodologies.