Safety
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
arXiv:2608.26889v1 Announce Type: new Abstract: Learning-augmented algorithms improve online decisions using predictions, but unreliable advice may harm efficiency and fairness. We study an online all
arXiv:2608.26889v1 Announce Type: new Abstract: Learning-augmented algorithms improve online decisions using predictions, but unreliable advice may harm efficiency and fairness. We study an online allocation problem with finite candidate sets, irreversible decisions, and exposure constraints. We propose a robust and fair rule combining advice with a conservative fallback and fairness correction. Under bounded-error assumptions, we prove consistency and robustness with loss proportional to prediction error. Experiments show stability under adversarial advice and significant reductions in exposure disparity.
Related
- Fairness under uncertainty in sequential decisions
- Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
- Credit Fairness: Online Fairness In Shared Resource Pools
- Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints
Source: arXiv cs.AI | 2026-08-28