arXiv:2509.05771v2 Announce Type: replace-cross Abstract: We develop a new classification framework based on the theory of coherent risk measures and systemic risk. The proposed approach is suitable for multi-class problems when the data is noisy, scarce (relative to the dimension of the problem), and the labeling might be unreliable. In the first part of our paper, we provide the foundation of the use of systemic risk models and show how to apply it in the context of linear and kernel-based multi-class problems. More advanced formulation via a system-theoretic approach with non-linear aggrega
The increasing deployment of AI in critical decision-making contexts necessitates robust methods for fair and reliable classification, particularly with imperfect data.
This research offers a pathway to more resilient and equitable AI systems by addressing data limitations and algorithmic bias through risk-averse approaches.
The ability to develop multi-class classification models that account for systemic risk and noisy, scarce, or unreliable data is enhanced.
- · AI ethics researchers
- · High-stakes AI deployment sectors (e.g., finance, healthcare)
- · Regulatory bodies
- · Data scientists
- · Developers of simplistic classification models
- · Organizations ignoring fairness in AI
Improved fairness and robustness in AI systems, especially in areas with sensitive data.
Increased trust in AI applications, leading to broader adoption in regulated industries.
Potential for new regulatory standards for AI systems derived from risk-averse principles.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG