Abstract— We develop a general framework for MAP estimation in discrete and Gaussian graphical models using Lagrangian relaxation techniques. The key idea is to reformulate an in...
Jason K. Johnson, Dmitry M. Malioutov, Alan S. Wil...
Abstract: Since von Neumann's seminal work around 1950, computer scientists and others have studied the algorithms needed to support self-replicating systems. Much of this wor...
We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Prev...
Failures triggered by hard to debug defects usually involve complex interactions between many program elements. We hypothesize that information flows present a good model for such ...
In POPL 2002, Petrank and Rawitz showed a universal result-finding optimal data placement is not only NP-hard but also impossible to approximate within a constant factor if P = NP...