arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.08441cs.LGstat.ML
收藏

具有不确定反馈图的在线学习

Online Learning with Uncertain Feedback Graphs

University of California, Irvine(加州大学欧文分校)

Pouya M Ghari, Yanning Shen

摘要:

通过专家建议进行的在线学习广泛用于各种机器学习任务。它考虑的问题是,学习者从一组专家中选择一个来接受建议并做出决定。在许多学习问题中,专家可能是相关的,因此学习者可以观察到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,该反馈图可以用于帮助学习者做出决策。然而,在实践中,名义反馈图往往带有不确定性,这使得它不可能揭示专家之间的实际关系。为了应对这一挑战,目前的工作研究各种情况下的潜在不确定性,并开发新的在线学习算法来处理不确定性,同时利用不确定反馈图。在较弱的条件下证明了所提算法具有次线性后悔性。在真实数据集上的实验证明了新算法的有效性。

英文摘要:

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.

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。

↑