无需预知损失上限，实时聚合专家预测的高效算法

Online Algorithm for Aggregating Experts' Predictions with Unbounded Quadratic Loss

• 通过指数加权调整专家损失，动态更新预测权重
• 在无界损失条件下仍保持稳定性能，理论误差可控
• 适合实际中损失范围未知的在线预测场景

我们研究在线聚合专家预测的问题，采用二次损失函数。提出一种无需事先知晓损失上界的聚合算法，基于专家损失的指数重加权机制，实现对不确定损失范围下的有效预测融合，保证了算法在无界损失条件下的稳定性与收敛性。

原文摘要 · Abstract (English)

We consider the problem of online aggregation of expert predictions with the quadratic loss function. We propose an algorithm for aggregating expert predictions which does not require a prior knowledge of the upper bound on the losses. The algorithm is based on the exponential reweighing of expert losses.

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。