TY - GEN
T1 - Adversarial online learning with noise
AU - Resler, Alon
AU - Mansour, Yishay
N1 - Publisher Copyright:
© 2019 International Machine Learning Society (IMLS).
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85078238871&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85078238871
T3 - 36th International Conference on Machine Learning, ICML 2019
SP - 9506
EP - 9514
BT - 36th International Conference on Machine Learning, ICML 2019
PB - International Machine Learning Society (IMLS)
T2 - 36th International Conference on Machine Learning, ICML 2019
Y2 - 9 June 2019 through 15 June 2019
ER -