REVIEW 17 cited by
Equality of Opportunity in Supervised Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Equality of Opportunity in Supervised Learning
read the original abstract
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. In line with other studies, our notion is oblivious: it depends only on the joint statistics of the predictor, the target and the protected attribute, but not on interpretation of individualfeatures. We study the inherent limits of defining and identifying biases based on such oblivious measures, outlining what can and cannot be inferred from different oblivious tests. We illustrate our notion using a case study of FICO credit scores.
Forward citations
Cited by 17 Pith papers
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
FairDiffuseVQVAE reaches state-of-the-art fairness on the standard tabular benchmark (DPR 0.702, EOR 0.686) by uniform protected-attribute sampling at inference, paying ~15 AUC points of utility.
-
A Model for Imbalanced Label Aggregation: A Focus on Minority-Class Detection
CC-Rasch recovers rare labels better than standard aggregators by letting both annotator competence and item difficulty vary by class, with supporting theory for majority vote under imbalance.
-
Unequal Trips, Unequal Places: Diagnosing and Mitigating Delay Inequity in Autonomous Vehicle Fleet Coordination
Budgeted congestion-responsive rerouting of the most delayed AVs cuts fleet overhead and origin-side delay inequity on three real-city networks without full-fleet replanning.
-
AgentFairBench: Do LLM Agents Discriminate When They Act?
AgentFairBench is a multi-domain benchmark for demographic disparity in LLM agent actions, with a pilot showing no significant effect for Claude Haiku 4.5 after arity-matched noise correction.
-
Frankenstein in the Pipeline: Computational Epistemicide in Facial Recognition
Facial recognition enacts computational epistemicide by progressively reducing faces to standardized numerical vectors, rendering reformist ethical AI insufficient and requiring abolition of vectorized identity as a b...
-
Landseer: Exploring the Machine Learning Defense Landscape
Landseer offers a containerized modular system to integrate and evaluate combinations of machine learning defenses, with an initial analysis of 35 defenses highlighting replicability challenges.
-
Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems
The Pareto frontier of fair algorithmic decisions consists of deterministic group-specific threshold rules on predicted success probabilities, which can include upper bounds for some fairness metrics and holds indepen...
-
Revisiting Fairness Impossibility with Endogenous Behavior
Error-rate balance and predictive parity become compatible under endogenous behavior by adjusting stakes differently across groups, introducing a new form of unequal treatment in consequences.
-
Differentiable Normative Guidance for Nash Bargaining Solution Recovery
Guided graph diffusion with a differentiable Nash-product penalty recovers individually rational, near-Nash-bargaining utility splits without explicit Pareto frontier knowledge.
-
Ethical and social risks of harm from Language Models
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job...
-
From Awareness to Action: Understanding and Overcoming the Research-Practice Gap in Algorithmic Fairness for Public Health
A mixed-methods investigation of the research-practice gap in algorithmic fairness for public health identifies barriers and proposes the Fairness-to-Action framework integrating methodological, organizational, and sy...
-
FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment
Zero-shot vision-language models are unreliable and vary widely for depression screening, and explainability-based fairness interventions often trade away accuracy without reliable fairness gains.
-
A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data
A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.
-
Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback
Develops a bandit algorithm with graph feedback that learns weights for multiple fairness constraints adaptively over sequential interactions.
-
FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment
Vision-language models for wellbeing assessment exhibit dataset-dependent performance and demographic biases, with explainability interventions providing inconsistent fairness gains at potential accuracy costs.
-
Man and machine: artificial intelligence and judicial decision making
A synthetic review across multiple fields concludes that AI decision aids have modest or nonexistent effects on judicial outcomes while identifying gaps in understanding human-AI interactions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.