Prediction against a limited adversary

Erhan Bayraktar; Ibrahim Ekren; Xin Zhang

Prediction against a limited adversary

Erhan Bayraktar, Ibrahim Ekren, Xin Zhang

Finance and Risk Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

We study the problem of prediction with expert advice with adversarial corruption where the adversary can at most corrupt one expert. Using tools from viscosity theory, we characterize the long-time behavior of the value function of the game between the forecaster and the adversary. We provide lower and upper bounds for the growth rate of regret without relying on a comparison result. We show that depending on the description of regret, the limiting behavior of the game can significantly differ.

Original language	English (US)
Journal	Journal of Machine Learning Research
Volume	22
State	Published - 2021

Keywords

Asymptotic expansion
Discontinuous viscosity solutions
Expert advice framework
Machine learning

ASJC Scopus subject areas

Control and Systems Engineering
Software
Statistics and Probability
Artificial Intelligence

Cite this

@article{fcb96831e0814dd3a83e2c05aa4b5fd4,

title = "Prediction against a limited adversary",

abstract = "We study the problem of prediction with expert advice with adversarial corruption where the adversary can at most corrupt one expert. Using tools from viscosity theory, we characterize the long-time behavior of the value function of the game between the forecaster and the adversary. We provide lower and upper bounds for the growth rate of regret without relying on a comparison result. We show that depending on the description of regret, the limiting behavior of the game can significantly differ.",

keywords = "Asymptotic expansion, Discontinuous viscosity solutions, Expert advice framework, Machine learning",

author = "Erhan Bayraktar and Ibrahim Ekren and Xin Zhang",

note = "Publisher Copyright: {\textcopyright} 2021 Erhan Bayraktar, Ibrahim Ekren and Xin Zhang.",

year = "2021",

language = "English (US)",

volume = "22",

journal = "Journal of Machine Learning Research",

issn = "1532-4435",

publisher = "Microtome Publishing",

}

TY - JOUR

T1 - Prediction against a limited adversary

AU - Bayraktar, Erhan

AU - Ekren, Ibrahim

AU - Zhang, Xin

PY - 2021

Y1 - 2021

N2 - We study the problem of prediction with expert advice with adversarial corruption where the adversary can at most corrupt one expert. Using tools from viscosity theory, we characterize the long-time behavior of the value function of the game between the forecaster and the adversary. We provide lower and upper bounds for the growth rate of regret without relying on a comparison result. We show that depending on the description of regret, the limiting behavior of the game can significantly differ.

AB - We study the problem of prediction with expert advice with adversarial corruption where the adversary can at most corrupt one expert. Using tools from viscosity theory, we characterize the long-time behavior of the value function of the game between the forecaster and the adversary. We provide lower and upper bounds for the growth rate of regret without relying on a comparison result. We show that depending on the description of regret, the limiting behavior of the game can significantly differ.

KW - Asymptotic expansion

KW - Discontinuous viscosity solutions

KW - Expert advice framework

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85105844594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85105844594&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85105844594

SN - 1532-4435

VL - 22

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

ER -

Prediction against a limited adversary

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this