Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
This paper describes an efficient reduction of the learning problem of ranking to binary classification. The reduction guarantees an average pairwise misranking regret of at most t...
We study the potential benefits to classification prediction that arise from having access to unlabeled samples. We compare learning in the semi-supervised model to the standard, ...
The problem of how a teacher and a learner can cooperate in the process of learning concepts from examples in order to minimize the required sample size without “coding tricksâ€...
Sandra Zilles, Steffen Lange, Robert Holte, Martin...
We analyze a sequential game between a Gambler and a Casino. The Gambler allocates bets from a limited budget over a fixed menu of gambling events that are offered at equal time i...