Timezone: »

 
Poster
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric
Nirandika Wanigasekara · Christina Yu

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #7
in Algorithms -- Bandit Algorithms »
Consider a nonparametric contextual multi-arm bandit problem where each arm $a \in [K]$ is associated to a nonparametric reward function $f_a: [0,1] \to \mathbb{R}$ mapping from contexts to the expected reward. Suppose that there is a large set of arms, yet there is a simple but unknown structure amongst the arm reward functions, e.g. finite types or smooth with respect to an unknown metric space. We present a novel algorithm which learns data-driven similarities amongst the arms, in order to implement adaptive partitioning of the context-arm space for more efficient learning. We provide regret bounds along with simulations that highlight the algorithm's dependence on the local geometry of the reward functions.
Keywords: Bandit Algorithms · Collaborative Filtering · Algorithms · Algorithms -> Clustering; Algorithms
[ Paper]  [ Slides] 

Author Information

Nirandika Wanigasekara (National University of Singapore)
Christina Yu (Cornell University)

More from the Same Authors