Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures.
Hamish FlynnDavid ReebMelih KandemirJan PetersPublished in: CoRR (2023)
Keyphrases
- regret bounds
- upper bound
- upper and lower bounds
- data structure
- lower bound
- significant improvement
- worst case
- optimization problems
- learning algorithm
- search algorithm
- computationally efficient
- generalization error bounds
- stochastic systems
- linear space
- average case
- blind source separation
- linear regression
- error bounds
- closed form
- machine learning algorithms
- expectation maximization
- online learning
- decision trees