Skip to yearly menu bar Skip to main content


Poster

Adversarial Online Learning with noise

Alon Resler · Yishay Mansour

Pacific Ballroom #156

Keywords: [ Bandits ] [ Online Learning ]


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.

Live content is unavailable. Log in and register to view live content