There has been a recent, growing interest in classification and link prediction in structured domains. Methods such as conditional random fields and relational Markov networks sup...
We study online learnability of a wide class of problems, extending the results of [26] to general notions of performance measure well beyond external regret. Our framework simult...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
Abstract. Differential repetitive processes are a distinct class of continuous-discrete twodimensional linear systems of both systems theoretic and applications interest. These pr...
Michael Dymkov, Eric Rogers, Siarhei Dymkou, Krzys...
Generally speaking, in the e-learning systems, a course is modeled as a graph, where each node represents a knowledge node (KU) and two nodes are connected to form a semantic netw...
Rules are commonly used for classification because they are modular, intelligible and easy to learn. Existing work in classification rule learning assumes the goal is to produce ca...