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 provide a general framework for learning precise, compact, and fast representations of the Bayesian predictive distribution for a model. This framework is based on minimizing t...
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Computational models of grounded language learning have been based on the premise that words and concepts are learned simultaneously. Given the mounting cognitive evidence for conc...
—In open multiagent systems, agents need to model their environments in order to identify trustworthy agents. Models of the environment should be accurate so that decisions about...