The increasing complexity of summarization systems makes it difficult to analyze exactly which modules make a difference in performance. We carried out a principled comparison be...
We consider the stochastic variant of the Canadian Traveler's Problem, a path planning problem where adverse weather can cause some roads to be untraversable. The agent does ...
We introduce anytime mechanisms for distributed optimization with self-interested agents. Anytime mechanisms retain good incentive properties even when interrupted before the opti...
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
We present an algorithm that takes an unannotated corpus as its input, and returns a ranked list of probable morphologically related pairs as its output. The algorithm tries to di...