# The Fairness-Accuracy Pareto Front

arXiv: https://arxiv.org/abs/2008.10797 · HTML: https://mlsanity.com/paper/2008.10797/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2020.

## Built on by (most cited first, 26 of 26)

- [Fair Normalizing Flows](https://mlsanity.com/paper/2106.05937/) (2021)
- [Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting](https://mlsanity.com/paper/2509.11452/) (2025)
- [Counterfactual Fairness with Partially Known Causal Graph](https://mlsanity.com/paper/2205.13972/) (2022)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [Evaluating Proposed Fairness Models for Face Recognition Algorithms](https://mlsanity.com/paper/2203.05051/) (2022)
- [Fairness Without Harm: An Influence-Guided Active Sampling Approach](https://mlsanity.com/paper/2402.12789/) (2024)
- [Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach](https://mlsanity.com/paper/2401.10632/) (2024)
- [Navigating Fairness Measures and Trade-Offs](https://mlsanity.com/paper/2307.08484/) (2023)
- [Generalization In Multi-Objective Machine Learning](https://mlsanity.com/paper/2208.13499/) (2022)
- [Entropy-driven Fair and Effective Federated Learning](https://mlsanity.com/paper/2301.12407/) (2023)
- [The Limits of Fair Medical Imaging AI In The Wild](https://mlsanity.com/paper/2312.10083/) (2023)
- [Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech](https://mlsanity.com/paper/2204.07661/) (2022)
- [Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives](https://mlsanity.com/paper/2502.16841/) (2025)
- [The Statistical Fairness-Accuracy Frontier](https://mlsanity.com/paper/2508.17622/) (2025)
- [A Hybrid 2-stage Neural Optimization for Pareto Front Extraction](https://mlsanity.com/paper/2101.11684/) (2021)
- [Achievable Fairness on Your Data With Utility Guarantees](https://mlsanity.com/paper/2402.17106/) (2024)
- [Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimality](https://mlsanity.com/paper/2404.08230/) (2024)
- [Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models](https://mlsanity.com/paper/2502.21123/) (2025)
- [Uncovering Cross-Objective Interference in Multi-Objective Alignment](https://mlsanity.com/paper/2602.06869/) (2026)
- [Towards Harmless Rawlsian Fairness Regardless of Demographic Prior](https://mlsanity.com/paper/2411.02467/) (2024)
- [A Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems](https://mlsanity.com/paper/2503.11120/) (2025)
- [First-See-Then-Design: A Multi-Stakeholder View for Optimal Performance-Fairness Trade-Offs](https://mlsanity.com/paper/2604.14035/) (2026)
- [Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems](https://mlsanity.com/paper/2605.10604/) (2026)
- [You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time](https://mlsanity.com/paper/2503.07066/) (2025)
- [The Pok'emon Theorem and other Fairness Impossibility Results](https://mlsanity.com/paper/2605.09221/) (2026)
- [GESD: Beyond Outcome-Oriented Fairness](https://mlsanity.com/paper/2605.15295/) (2026)

## Abstract (arXiv)

Algorithmic fairness seeks to identify and correct sources of bias in machine learning algorithms. Confoundingly, ensuring fairness often comes at the cost of accuracy. We provide formal tools in this work for reconciling this fundamental tension in algorithm fairness. Specifically, we put to use the concept of Pareto optimality from multi-objective optimization and seek the fairness-accuracy Pareto front of a neural network classifier. We demonstrate that many existing algorithmic fairness methods are performing the so-called linear scalarization scheme which has severe limitations in recovering Pareto optimal solutions. We instead apply the Chebyshev scalarization scheme which is provably superior theoretically and no more computationally burdensome at recovering Pareto optimal solutions compared to the linear scheme.