跟随扰动领导者的自适应在线预测
Adaptive Online Prediction by Following the Perturbed Leader
摘要：
在将聚合策略应用于专家建议预测时，必须自适应地调整学习率。sqrt（复杂性/当前损失）的自然选择使得加权多数衍生工具的分析非常复杂。特别是，对于任意权重，迄今为止还没有证明结果。Kalai & Vempala（2003）的“Follow the Perturbed Leader”（FPL）算法（基于Hannan的算法）的分析更容易。我们得到的损失界自适应学习率和有限的专家类与统一的权重和可数的专家类与任意的权重。对于前一种设置，我们的损失界匹配到目前为止最知名的结果，而对于后者，我们的结果是新的。
英文摘要：
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no results proven so far. The analysis of the alternative "Follow the Perturbed Leader" (FPL) algorithm from Kalai & Vempala (2003) (based on Hannan's algorithm) is easier. We derive loss bounds for adaptive learning rate and both finite expert classes with uniform weights and countable expert classes with arbitrary weights. For the former setup, our loss bounds match the best known results so far, while for the latter our results are new.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
