Search Results for author:
Found 1 papers, 0 papers with code
Cascaded Algorithm-Selection and Hyper-Parameter Optimization with Extreme-Region Upper Confidence Bound Bandit
We show theoretically that the ER-UCB has a regret upper bound $O\left(K \ln n\right)$ with independent feedbacks, which is as efficient as the classical UCB bandit.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
