Novel Bounds on the Probability of Misclassification in Majority Voting: Leveraging the Majority Size

A.T.J.R. Cobbenhagen; A. Carè; M.C. Campi; F.A. Ramponi; D.J. Antunes; W.P.M.H. Heemels

doi:10.1109/LCSYS.2020.3040961

Novel Bounds on the Probability of Misclassification in Majority Voting: Leveraging the Majority Size

A.T.J.R. Cobbenhagen (Corresponding author), A. Carè, M.C. Campi, F.A. Ramponi, D.J. Antunes, W.P.M.H. Heemels

Onderzoeksoutput: Bijdrage aan tijdschrift › Tijdschriftartikel › Academic › peer review

1 Citaat (Scopus)

Samenvatting

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.

Originele taal-2	Engels
Artikelnummer	9272617
Pagina's (van-tot)	1513-1518
Aantal pagina's	6
Tijdschrift	IEEE Control Systems Letters
Volume	5
Nummer van het tijdschrift	5
DOI's	https://doi.org/10.1109/LCSYS.2020.3040961
Status	Gepubliceerd - nov. 2021

Financiering

Manuscript received September 14, 2020; revised November 14, 2020; accepted November 18, 2020. Date of publication November 26, 2020; date of current version December 22, 2020. The work of A. T. J. R. Cobbenhagen, D. J. Antunes, and W. P. M. H. Heemels were supported by “Toeslag voor Topconsortia voor Kennis en Innovatie” (TKI HTSM) from the Ministry of Economic Affairs, the Netherlands. The work of A. Carè, M. C. Campi, and F. A. Ramponi were supported by the H&W Program of the University of Brescia under Project CLAFITE. Recommended by Senior Editor G. Cherubini. (Corresponding author: A. T. J. R. Cobbenhagen.) A. T. J. R. Cobbenhagen, D. J. Antunes, and W. P. M. H. Heemels are with the Department of Mechanical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands (e-mail: [email protected]; [email protected]; [email protected]). The work of A. T. J. R. Cobbenhagen, D. J. Antunes, and W. P. M. H. Heemels were supported by ?Toeslag voor Topconsortia voor Kennis en Innovatie? (TKI HTSM) from the Ministry of Economic Affairs, the Netherlands. The work of A. Car?, M. C. Campi, and F. A. Ramponi were supported by the H&W Program of the University of Brescia under Project CLAFITE.

Financiers	Financiernummer
Topconsortia voor Kennis en Innovatie?
Agentschap voor Innovatie door Wetenschap en Technologie
Ministerie van Economische Zaken en Klimaat
University of Brescia

Toegang tot document

10.1109/LCSYS.2020.3040961

Andere bestanden en links

Link to publication in Scopus

Citeer dit

@article{e8a263fa70da4c17879e02b56f9c7de8,

title = "Novel Bounds on the Probability of Misclassification in Majority Voting: Leveraging the Majority Size",

abstract = "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. ",

keywords = "agents-based systems, Machine learning, statistical learning",

author = "A.T.J.R. Cobbenhagen and A. Car{\`e} and M.C. Campi and F.A. Ramponi and D.J. Antunes and W.P.M.H. Heemels",

year = "2021",

month = nov,

doi = "10.1109/LCSYS.2020.3040961",

language = "English",

volume = "5",

pages = "1513--1518",

journal = "IEEE Control Systems Letters",

issn = "2475-1456",

publisher = "Institute of Electrical and Electronics Engineers",

number = "5",

}

TY - JOUR

T1 - Novel Bounds on the Probability of Misclassification in Majority Voting: Leveraging the Majority Size

AU - Cobbenhagen, A.T.J.R.

AU - Carè, A.

AU - Campi, M.C.

AU - Ramponi, F.A.

AU - Antunes, D.J.

AU - Heemels, W.P.M.H.

PY - 2021/11

Y1 - 2021/11

N2 - 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.

AB - 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.

KW - agents-based systems

KW - Machine learning

KW - statistical learning

UR - http://www.scopus.com/inward/record.url?scp=85098552590&partnerID=8YFLogxK

U2 - 10.1109/LCSYS.2020.3040961

DO - 10.1109/LCSYS.2020.3040961

M3 - Article

AN - SCOPUS:85098552590

SN - 2475-1456

VL - 5

SP - 1513

EP - 1518

JO - IEEE Control Systems Letters

JF - IEEE Control Systems Letters

IS - 5

M1 - 9272617

ER -

Novel Bounds on the Probability of Misclassification in Majority Voting: Leveraging the Majority Size

Samenvatting

Financiering

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit