用预测提升在线分配效率，同时防错保公平
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
- 融合预测与保守回退策略，动态调整分配决策
- 预测误差越小，性能损失越低，最差情况仍稳定
- 适合需要公平曝光的资源分配场景
学习增强型算法利用预测信息优化在线决策，但不可靠的建议可能损害效率与公平性。本文研究具有有限候选集、不可逆决策和曝光约束的在线分配问题。提出一种鲁棒且公平的分配规则，将建议与保守回退机制结合，并引入公平性修正。在预测误差有界条件下，证明了算法的一致性与鲁棒性，性能损失与预测误差成正比。实验表明，该方法在对抗性建议下仍保持稳定，并显著降低曝光不平等现象。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。