A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes
Fair representation learning with a continuous sensitive attribute $S$ requires a representation $Z$ that is statistically independent of $S$. Existing criteria, including generalized demographic parity, the expectation of integral probability metrics (EIPM), and mutual information, enforce this independence by averaging a per-value discrepancy between the conditional law $P_{Z \mid S=s}$ and the marginal $P_Z$ over the law of $S$. This approach requires a nonparametric surrogate for the conditi
Record details
Published: 11 August 2026
Source: arXiv fairness query
Category: Research
Topics: Regulation
Retrieved: 12 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
What We Know about Responsible AI Practices in Industry: A Half Decade of Empirical Research
arXiv · 11 August 2026
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning
arXiv · 11 August 2026
Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning
arXiv · 11 August 2026
Inferential Capability Does Not Determine Legal Scope
arXiv · 11 August 2026
IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning
arXiv cs.LG · 11 August 2026
Longitudinal Evidence That General-Purpose Chatbots Actively Foster Relational Engagement
arXiv · 11 August 2026
How to cite this record
ethics.ai (11 August 2026), “A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes,” evidence record 18680, https://ethics.ai/record/18680 (originally published by arXiv fairness query).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.