Adversarial Online Learning with Noise
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.
Cite
Text
Resler and Mansour. "Adversarial Online Learning with Noise." International Conference on Machine Learning, 2019.Markdown
[Resler and Mansour. "Adversarial Online Learning with Noise." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/resler2019icml-adversarial/)BibTeX
@inproceedings{resler2019icml-adversarial,
title = {{Adversarial Online Learning with Noise}},
author = {Resler, Alon and Mansour, Yishay},
booktitle = {International Conference on Machine Learning},
year = {2019},
pages = {5429-5437},
volume = {97},
url = {https://mlanthology.org/icml/2019/resler2019icml-adversarial/}
}