Online Boosting with Bandit Feedback
This work addresses the problem of online learning with bandit feedback for regression tasks, offering incremental improvements in efficiency for machine learning practitioners.
The paper tackles online boosting for regression with limited feedback, presenting an efficient regret minimization method that yields an algorithm for noisy multi-point bandit feedback and a projection-free online convex optimization algorithm with improved efficiency guarantees.
We consider the problem of online boosting for regression tasks, when only limited information is available to the learner. We give an efficient regret minimization method that has two implications: an online boosting algorithm with noisy multi-point bandit feedback, and a new projection-free online convex optimization algorithm with stochastic gradient, that improves state-of-the-art guarantees in terms of efficiency.