The problem of task assignment naturally arises in multiagent multitask systems, where an optimal matching of agents and tasks is sought. This problem is a combinatorial optimizati...
The problem of automatic feature selection/weighting in kernel methods is examined. We work on a formulation that optimizes both the weights of features and the parameters of the ...
Our main result is a reduction from worst-case lattice problems such as GAPSVP and SIVP to a certain learning problem. This learning problem is a natural extension of the `learnin...
Schema matching is one of the key challenges in information integration. It is a labor-intensive and time-consuming process. To alleviate the problem, many automated solutions have...
This paper introduces dual decomposition as a framework for deriving inference algorithms for NLP problems. The approach relies on standard dynamic-programming algorithms as oracl...
Alexander M. Rush, David Sontag, Michael Collins, ...