Online Learning With Uncertain Feedback Graphs
Online Learning With Uncertain Feedback Graphs
复制标题
具有不确定反馈图的在线学习
DOI：
10.1109/tnnls.2023.3235734
复制
发表时间：
2023
影响因子：
10.4
通讯作者：
Shen, Yanning
中科院分区：
文献类型：
--
作者：
Ghari, Pouya M.;Shen, Yanning
具有专家建议的在线学习广泛应用于各种机器学习任务中。它考虑学习者从一组专家中选择一个专家来听取建议并做出决定的问题。在许多学习问题中，专家可能是相关的，从此学习者可以观察与所选专家相关的专家子集相关的损失。在这种情况下，专家之间的关系可以通过反馈图来捕获，可以用来帮助学习者做出决策。然而，在实践中，名义反馈图往往具有不确定性，无法揭示专家之间的实际关系。为了应对这一挑战，目前的工作研究了各种潜在不确定性的情况，并开发了新颖的在线学习算法来处理不确定性，同时利用不确定性反馈图。事实证明，所提出的算法在温和条件下具有亚线性遗憾。在真实数据集上进行的实验证明了新算法的有效性。
Online learning with expert advice is widely used in various machine learning tasks. It considers the problem where a learner chooses one from a set of experts to take advice and make a decision. In many learning problems, experts may be related, henceforth the learner can observe the losses associated with a subset of experts that are related to the chosen one. In this context, the relationship among experts can be captured by a feedback graph, which can be used to assist the learner’s decision-making. However, in practice, the nominal feedback graph often entails uncertainties, which renders it impossible to reveal the actual relationship among experts. To cope with this challenge, the present work studies various cases of potential uncertainties and develops novel online learning algorithms to deal with uncertainties while making use of the uncertain feedback graph. The proposed algorithms are proved to enjoy sublinear regret under mild conditions. Experiments on real datasets are presented to demonstrate the effectiveness of the novel algorithms.