UCBoost: A Boosting Approach to Tame Complexity and Optimality for Stochastic Bandits

no code implementations • 16 Apr 2018 • Fang Liu, Sinong Wang, Swapna Buccapatnam, Ness Shroff

We show that UCBoost($D$) enjoys $O(1)$ complexity for each arm per round as well as regret guarantee that is $1/e$-close to that of the kl-UCB algorithm.

Decision Making

Information Directed Sampling for Stochastic Bandits with Graph Feedback

no code implementations • 8 Nov 2017 • Fang Liu, Swapna Buccapatnam, Ness Shroff

We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action.

Decision Making Thompson Sampling

Reward Maximization Under Uncertainty: Leveraging Side-Observations on Networks

no code implementations • 26 Apr 2017 • Swapna Buccapatnam, Fang Liu, Atilla Eryilmaz, Ness B. Shroff

We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions that occur as a result of an underlying network structure.