Prediction against a limited adversary
Machine Learning
2021-03-02 v3 Probability
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
Cite
@article{arxiv.2011.01217,
title = {Prediction against a limited adversary},
author = {Erhan Bayraktar and Ibrahim Ekren and Xin Zhang},
journal= {arXiv preprint arXiv:2011.01217},
year = {2021}
}
Comments
To appear in Journal of Machine Learning Research (JMLR). Keywords: machine learning, expert advice framework, asymptotic expansion, discontinuous viscosity solutions