Statistical and Structural Approaches to Algorithmic Fairness

• URL: http://arxiv.org/abs/2606.26200v1
• Date: Wed, 24 Jun 2026 16:23:40 GMT
• Title: Statistical and Structural Approaches to Algorithmic Fairness
• Abstract summary: Modern machine learning systems have outgrown their origins as isolated predictive constructs.<n>The field of algorithmic fairness emerged in response to the growing recognition that models optimized for predictive accuracy can systematically disadvantage marginalized groups.<n>This thesis identifies and addresses two fundamental limitations of contemporary fairness paradigms.
• Score: 0.27756462755759775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern machine learning systems have outgrown their origins as isolated predictive constructs, evolving into complex socio-technical architectures that actively mediate human opportunity. As algorithms increasingly determine access to economic and social opportunities, it has become widely recognized that these systems are deeply embedded with the structural inequalities and prejudices of their environments. The field of algorithmic fairness emerged in response to the growing recognition that models optimized for predictive accuracy can systematically disadvantage marginalized groups. Early mitigation strategies, however, rested on fragile simplifications that limited their effectiveness in complex socio-technical environments. This thesis identifies and addresses two fundamental limitations of contemporary fairness paradigms: the reliance on deterministic point estimates for auditing and the treatment of individuals as isolated entities devoid of structural context.

Related papers

• On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective [0.0]
  In this work we examine intrinsic limits of data-driven decision systems from an information-theoretic and interaction-based perspective.<n>We analyze minimal achievable error in classification through Fano-type bounds and precision limits in parametric estimation via the Cramér-Rao inequality.
  arXiv  Detail & Related papers  (2026-08-13T17:34:41Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• A Feminist Account of Intersectional Algorithmic Fairness [0.0]
  We propose Substantive Intersectional Algorithmic Fairness, extending Green's notion of substantive algorithmic fairness with insights from intersectional feminist theory.<n>We introduce ten desiderata within the ROOF methodology to guide the design, assessment, and deployment of algorithmic systems.<n>By bridging computational and social science perspectives, we provide actionable guidance for more equitable, inclusive, and context-sensitive intersectional algorithmic practices.
  arXiv  Detail & Related papers  (2025-08-25T12:09:04Z)
• Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot [44.336297829718795]
  We introduce CATE-B, an open-source co-pilot system that uses large language models (LLMs) within an agentic framework to guide users through treatment effect estimation.<n>CATE-B assists in (i) constructing a structural causal model via causal discovery and LLM-based edge orientation, (ii) identifying robust adjustment sets through a novel Minimal Uncertainty Adjustment Set criterion, and (iii) selecting appropriate regression methods tailored to the causal structure and dataset characteristics.
  arXiv  Detail & Related papers  (2025-08-14T12:20:51Z)
• Secondary Bounded Rationality: A Theory of How Algorithms Reproduce Structural Inequality in AI Hiring [0.174048653626208]
  Article argues that AI systems inherit and amplify human cognitive and structural biases through technical and sociopolitical constraints.<n>We show how algorithmic processes transform historical inequalities, such as elite credential privileging and network homophily, into ostensibly meritocratic outcomes.<n>We propose mitigation strategies, including counterfactual fairness testing, capital-aware auditing, and regulatory interventions, to disrupt this self-reinforcing inequality.
  arXiv  Detail & Related papers  (2025-07-12T10:03:20Z)
• Algorithmic Fairness: Not a Purely Technical but Socio-Technical Property [4.2894701473635966]
  We argue that fairness cannot be reduced to purely technical constraints on models.<n>We examine the limitations of existing fairness measures through conceptual analysis and empirical illustrations.<n>We believe these findings will help bridge the gap between technical formalisation and social realities.
  arXiv  Detail & Related papers  (2025-06-14T15:54:45Z)
• What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks [16.795332276080888]
  We propose a fine-grained validation framework for explainable artificial intelligence systems. We recognise their inherent modular structure: technical building blocks, user-facing explanatory artefacts and social communication protocols.
  arXiv  Detail & Related papers  (2024-03-19T13:45:34Z)
• Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes [72.13373216644021]
  We study the societal impact of machine learning by considering the collection of models that are deployed in a given context. We find deployed machine learning is prone to systemic failure, meaning some users are exclusively misclassified by all models available. These examples demonstrate ecosystem-level analysis has unique strengths for characterizing the societal impact of machine learning.
  arXiv  Detail & Related papers  (2023-07-12T01:11:52Z)
• HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline [45.91245228386502]
  Existing SAT generation approaches can hardly simultaneously capture the global structural properties and maintain plausible computational hardness. We propose HardSATGEN, which introduces a fine-grained control mechanism to the neural split-merge paradigm for SAT formula generation. Compared to the best previous methods, the average performance gains achieve 38.5% in structural statistics, 88.4% in computational metrics, and over 140.7% in the effectiveness of guiding solver tuning.
  arXiv  Detail & Related papers  (2023-02-04T05:58:17Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.