Maximum Margin Matrix Factorization (MMMF) was recently suggested (Srebro et al., 2005) as a convex, infinite dimensional alternative to low-rank approximations and standard facto...
In recent work we showed that models constructed from planner performance data over a large suite of benchmark problems are surprisingly accurate; 91-99% accuracy for success and ...
Mark Roberts, Adele E. Howe, Brandon Wilson, Marie...
Learning disabilities are serious societal problems contributing to a loss of quality of life for affected individuals and their families. We hypothesized that the learning disabil...
H. Craig Heller, Damien Colas, Norman F. Ruby, Fab...
Abstract. Flexibility and automatic learning are key aspects to support users in dynamic business environments such as value chains across SMEs or when organizing a large event. Pr...
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...