{
  "abstract": "Fairness-accuracy trade-offs are a central concern in the deployment of fairness-aware machine learning methods. When sensitive attributes are unavailable at inference time-the so called unawareness setting, principled methods for obtaining accurate predictions under relaxed fairness constraints are largely missing. In this work, we address this gap by formulating regression under a demographic parity penalty as an optimal transport problem. Our framework, unifies both the aware and unaware settings and characterizes optimal prediction functions via optimal transport maps, under both squared Wasserstein-2 and Total Variation penalties. These results reveal that the choice of penalty reflects fundamentally different fairness philosophies: the Wasserstein penalty induces a smooth, population-wide compromise, while Total Variation enforces parity for a subset of individuals. Building on these theoretical characterizations, we propose FAUST, an algorithm that is simple to implement, computationally efficient, and consistently matches or outperforms state-of-the-art baselines on real-world benchmarks.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.28233",
  "author_total": 5,
  "authors": [
    {
      "name": "Marie Generali Lince"
    },
    {
      "name": "Vincent Divol"
    },
    {
      "name": "Rémi Flamary"
    },
    {
      "name": "Solenne Gaucher"
    },
    {
      "name": "Patrick Loiseau"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1enqps9w8yz7b.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.28233",
  "fulltext_url": null,
  "id": "1enqps9w8yz7b",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.28233",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CY"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "3311|Ethics and Social Impacts of AI"
    ]
  ],
  "openalex": "W7162638978",
  "pdf_url": "https://arxiv.org/pdf/2605.28233",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1enqps9w8yz7b.ris",
  "sources": [
    {
      "first_seen": "2026-11-02T12:21:25Z",
      "native_id": "2605.28233",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.28233"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings",
  "title_text": "Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings",
  "type": "preprint",
  "updated_at": "2026-11-04T15:20:53Z",
  "url": "https://research.draconitic.com/paper/1enqps9w8yz7b",
  "venue": "arXiv",
  "versions": []
}