We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
Sanjoy Dasgupta, Adam Tauman Kalai, Claire Montele...
Abstract. Despite significant progress in the development of Grid infrastructure, the provisioning of a customized and controllable remote execution environment remains an open iss...
Katarzyna Keahey, Ian T. Foster, Timothy Freeman, ...
Imbalanced data learning has recently begun to receive much attention from research and industrial communities as traditional machine learners no longer give satisfactory results. ...
The main objective of the Intelligent GRID Scheduling System (ISS) project is to provide a middleware infrastructure allowing a good positioning and scheduling of real life applic...
Ralf Gruber, Vincent Keller, Pierre Kuonen, Marie-...
MPI defines one-sided communication operations—put, get, and accumulate—together with three different synchronization mechanisms that define the semantics associated with th...