Online Boosting with Bandit Feedback
arXiv:2007.11975
Abstract
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.
References in corpus (8)
- Projection-free Online Learning
- Learning Adversarial MDPs with Bandit Feedback and Unknown Transition
- Online Gradient Boosting
- Optimal and Adaptive Algorithms for Online Boosting
- Projection-Free Bandit Convex Optimization
- Functional Frank-Wolfe Boosting for General Loss Functions
- Improved Regret Bounds for Projection-free Bandit Convex Optimization
- Online Agnostic Boosting via Regret Minimization