Adversarial Online Learning with noise

[edit]

Alon Resler, Yishay Mansour ;
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:5429-5437, 2019.

Abstract

We present and study models of adversarial online learning where the feedback observed by the learner is noisy, and the feedback is either full information feedback or bandit feedback. Specifically, we consider binary losses xored with the noise, which is a Bernoulli random variable. We consider both a constant noise rate and a variable noise rate. Our main results are tight regret bounds for learning with noise in the adversarial online learning model.

Related Material