Corpus-based methods for natural language processing often use supervised training, requiring expensive manual annotation of training corpora. This paper investigates methods for ...
Owing to the stochastic nature of discrete processes such as photon counts in imaging, real-world data measurements often exhibit heteroscedastic behavior. In particular, time ser...
Modularity and symmetry are two properties observed in almost every engineering and biological structure. The origin of these properties in nature is still unknown. Yet, as engine...
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...
This paper introduces a robust approach to stochastic multi-hop routing for wireless networks when the quality of links is modelled through a reliability matrix R. Yielding to the ...
Yuchen Wu, Alejandro Ribeiro, Georgios B. Giannaki...