当前位置: X-MOL 学术 › IEEE Control Systems Letters › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Novel bounds on the probability of misclassification in majority voting: leveraging the majority size
IEEE Control Systems Letters Pub Date : 2021-11-01 , DOI: 10.1109/lcsys.2020.3040961
A. T. J. R. Cobbenhagen , A. Care , M. C. Campi , F. A. Ramponi , D. J. Antunes , W. P. M. H. Heemels

Majority voting is often employed as a tool to increase the robustness of data-driven decisions and control policies, a fact which calls for rigorous, quantitative evaluations of the limits and the potentials of majority voting schemes. This letter focuses on the case where the voting agents are binary classifiers and introduces novel bounds on the probability of misclassification conditioned on the size of the majority. We show that these bounds can be much smaller than the traditional upper bounds on the probability of misclassification. These bounds can be used in a ‘Probably Approximately Correct’ (PAC) setting, which allows for a practical implementation.

中文翻译:

多数表决中错误分类的可能性的新颖界限:利用多数票的规模

多数投票通常被用作提高数据驱动的决策和控制政策的鲁棒性的工具,这一事实要求对多数投票方案的限制和潜力进行严格,定量的评估。这封信的重点是投票代理人是二元分类器的情况,并介绍了以多数人的人数为条件的误分类概率的新颖界限。我们证明,在误分类的可能性上,这些界限可能比传统的界限小得多。这些界限可以在“可能近似正确”(PAC)设置中使用,从而可以进行实际实现。
更新日期:2021-11-01
down
wechat
bug