261 citations · 1.4k across the 45 of their papers we have counts for
4 papers · 1 filter
lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits
Kevin Jamieson, Matthew Malloy, Robert Nowak +1
The paper proposes a novel upper confidence bound (UCB) procedure for identifying the arm with the largest mean in a multi-armed bandit game in the fixed confidence setting using a…
On the local profiles of trees
Sébastien Bubeck, Nati Linial
We study the local profiles of trees. We show that, in contrast with the situation for general graphs, the limit set of k-profiles of trees is convex. We initiate a study of the de…
On Finding the Largest Mean Among Many
Kevin Jamieson, Matthew Malloy, Robert Nowak +1
Sampling from distributions to find the one with the largest mean arises in a broad range of applications, and it can be mathematically modeled as a multi-armed bandit problem in w…
Prior-free and prior-dependent regret bounds for Thompson Sampling
Sébastien Bubeck, Che-Yu Liu
We consider the stochastic multi-armed bandit problem with a prior distribution on the reward distributions. We are interested in studying prior-free and prior-dependent regret bou…