新方法实现在线校准，支持间歇反馈且记忆开销低。
Mirror Online Conformal Prediction with Intermittent Feedback
- 结合先验知识与间歇反馈，用镜像更新策略保持校准
- 保证长期覆盖概率，且后悔值呈次线性增长
- 适合实时系统中资源受限的智能模型校准
在线共形预测通过运行时反馈对预训练的人工智能模型进行性能校准。校准通过在线规则更新集合预测以确保长期覆盖保证。尽管近期研究证明引入先验知识可提升校准效果，但代价是将覆盖保证替换为基于分位数损失的较弱后悔保证。本文提出间歇镜像在线共形预测（IM-OCP），一种新型运行时校准框架，能融合先验知识、处理潜在间歇反馈，并具备极低内存复杂度。IM-OCP 在任意数据序列上均保证确定性的长期覆盖与次线性后悔，在间歇反馈下也满足期望层面的相同性质。
原文摘要 · Abstract (English)
Online conformal prediction enables the runtime calibration of a pre-trained artificial intelligence model using feedback on its performance. Calibration is achieved through set predictions that are updated via online rules so as to ensure long-term coverage guarantees. While recent research has demonstrated the benefits of incorporating prior knowledge into the calibration process, this has come at the cost of replacing coverage guarantees with less tangible regret guarantees based on the quantile loss. This work introduces intermittent mirror online conformal prediction (IM-OCP), a novel runtime calibration framework that integrates prior knowledge, operates under potentially intermittent feedback, and features minimal memory complexity. IM-OCP guarantees long-term coverage and sub-linear regret, both of which hold deterministically for any given data sequence and in expectation with respect to the intermittent feedback.
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。