What Constitutes a Less Discriminatory Algorithm?

• URL: http://arxiv.org/abs/2412.18138v2
• Date: Mon, 24 Mar 2025 16:25:45 GMT
• Title: What Constitutes a Less Discriminatory Algorithm?
• Authors: Benjamin Laufer, Manish Raghavan, Solon Barocas,
• Abstract summary: We argue that formal LDA definitions face fundamental challenges when they attempt to evaluate and compare predictive models in the absence of held-out data.<n>We put forward a framework in which both firms and plaintiffs can search for alternative models that comport with societal goals.
• Score: 2.842548870013324
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Disparate impact doctrine offers an important legal apparatus for targeting discriminatory data-driven algorithmic decisions. A recent body of work has focused on conceptualizing one particular construct from this doctrine: the less discriminatory alternative, an alternative policy that reduces disparities while meeting the same business needs of a status quo or baseline policy. However, attempts to operationalize this construct in the algorithmic setting must grapple with some thorny challenges and ambiguities. In this paper, we attempt to raise and resolve important questions about less discriminatory algorithms (LDAs). How should we formally define LDAs, and how does this interact with different societal goals they might serve? And how feasible is it for firms or plaintiffs to computationally search for candidate LDAs? We find that formal LDA definitions face fundamental challenges when they attempt to evaluate and compare predictive models in the absence of held-out data. As a result, we argue that LDA definitions cannot be purely quantitative, and must rely on standards of "reasonableness." We then identify both mathematical and computational constraints on firms' ability to efficiently conduct a proactive search for LDAs, but we provide evidence that these limits are "weak" in a formal sense. By defining LDAs formally, we put forward a framework in which both firms and plaintiffs can search for alternative models that comport with societal goals.

Related papers

• Understanding the Logic of Direct Preference Alignment through Logic [54.272600416107146]
  We propose a novel formalism for characterizing preference losses for single model and reference model based approaches. We show how this formal view of preference learning sheds new light on both the size and structure of the DPA loss landscape.
  arXiv  Detail & Related papers  (2024-12-23T16:23:13Z)
• Making Large Language Models Better Planners with Reasoning-Decision Alignment [70.5381163219608]
  We motivate an end-to-end decision-making model based on multimodality-augmented LLM. We propose a reasoning-decision alignment constraint between the paired CoTs and planning results. We dub our proposed large language planners with reasoning-decision alignment as RDA-Driver.
  arXiv  Detail & Related papers  (2024-08-25T16:43:47Z)
• Implementing Fairness in AI Classification: The Role of Explainability [0.0]
  We argue that implementing fairness in AI classification involves more work than just operationalizing a fairness metric. We make the training processes transparent, determining what outcomes the fairness criteria actually produce, and assessing their trade-offs. We draw conclusions regarding the way in which these explanatory steps can make an AI model trustworthy.
  arXiv  Detail & Related papers  (2024-07-20T06:06:24Z)
• The Legal Duty to Search for Less Discriminatory Algorithms [4.625678906362822]
  We argue that the law should place a duty of a reasonable search for LDAs. Model multiplicity and the availability of LDAs have significant ramifications for the legal response to discriminatory algorithms. We argue that the law should place a duty of a reasonable search for LDAs on entities that develop and deploy predictive models in covered civil rights domains.
  arXiv  Detail & Related papers  (2024-06-10T21:56:38Z)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data [102.16105233826917]
  Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning.
  arXiv  Detail & Related papers  (2024-04-22T17:20:18Z)
• Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales [54.78115855552886]
  We show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
  arXiv  Detail & Related papers  (2024-02-23T16:50:07Z)
• Federated Fairness without Access to Sensitive Groups [12.888927461513472]
  Current approaches to group fairness in federated learning assume the existence of predefined and labeled sensitive groups during training. We propose a new approach to guarantee group fairness that does not rely on any predefined definition of sensitive groups or additional labels.
  arXiv  Detail & Related papers  (2024-02-22T19:24:59Z)
• Alignment for Honesty [105.72465407518325]
  Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for emphhonesty, ensuring that LLMs proactively refuse to answer questions when they lack knowledge. We address these challenges by first establishing a precise problem definition and defining honesty'' inspired by the Analects of Confucius.
  arXiv  Detail & Related papers  (2023-12-12T06:10:42Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Fairness in Ranking under Disparate Uncertainty [24.401219403555814]
  We argue that ranking can introduce unfairness if the uncertainty of the underlying relevance model differs between groups of options. We propose Equal-Opportunity Ranking (EOR) as a new fairness criterion for ranking. We show that EOR corresponds to a group-wise fair lottery among the relevant options even in the presence of disparate uncertainty.
  arXiv  Detail & Related papers  (2023-09-04T13:49:48Z)
• Compatibility of Fairness Metrics with EU Non-Discrimination Laws: Demographic Parity & Conditional Demographic Disparity [3.5607241839298878]
  Empirical evidence suggests that algorithmic decisions driven by Machine Learning (ML) techniques threaten to discriminate against legally protected groups or create new sources of unfairness. This work aims at assessing up to what point we can assure legal fairness through fairness metrics and under fairness constraints. Our experiments and analysis suggest that AI-assisted decision-making can be fair from a legal perspective depending on the case at hand and the legal justification.
  arXiv  Detail & Related papers  (2023-06-14T09:38:05Z)
• Beyond Incompatibility: Trade-offs between Mutually Exclusive Fairness Criteria in Machine Learning and Law [2.959308758321417]
  We present a novel algorithm (FAir Interpolation Method: FAIM) for continuously interpolating between three fairness criteria. We demonstrate the effectiveness of our algorithm when applied to synthetic data, the COMPAS data set, and a new, real-world data set from the e-commerce sector.
  arXiv  Detail & Related papers  (2022-12-01T12:47:54Z)
• 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)
• Developing a Philosophical Framework for Fair Machine Learning: Lessons From The Case of Algorithmic Collusion [0.0]
  As machine learning algorithms are applied in new contexts the harms and injustices that result are qualitatively different. The existing research paradigm in machine learning which develops metrics and definitions of fairness cannot account for these qualitatively different types of injustice. I propose an ethical framework for researchers and practitioners in machine learning seeking to develop and apply fairness metrics.
  arXiv  Detail & Related papers  (2022-07-05T16:21:56Z)
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
  We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA) DALN achieves explicit domain alignment and category distinguishment through a unified objective. DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
  arXiv  Detail & Related papers  (2022-04-08T04:40:18Z)
• Fairness-Aware Naive Bayes Classifier for Data with Multiple Sensitive Features [0.0]
  We generalise two-naive-Bayes (2NB) into N-naive-Bayes (NNB) to eliminate the simplification of assuming only two sensitive groups in the data. We investigate its application on data with multiple sensitive features and propose a new constraint and post-processing routine to enforce differential fairness.
  arXiv  Detail & Related papers  (2022-02-23T13:32:21Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)

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.