We deploy a novel Reinforcement Learning optimization technique based on afterstates learning to determine the gain that can be achieved by incorporating movement prediction inform...
Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation...
Ofer Meshi, David Sontag, Tommi Jaakkola, Amir Glo...
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
The detection and improvement of low-quality information is a key concern in Web applications that are based on user-generated content; a popular example is the online encyclopedi...