This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009...
Abstract—We consider two desired properties of learning algorithms: sparsity and algorithmic stability. Both properties are believed to lead to good generalization ability. We sh...
—It has been shown that the Universum data, which do not belong to either class of the classification problem of interest, may contain useful prior domain knowledge for training...
A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently...
In today’s homes and schools, children are emerging as frequent and experienced users of technology [3, 14]. As this trend continues, it becomes increasingly important to ask if...