Bisubmodularity extends the concept of submodularity to set functions with two arguments. We show how bisubmodular maximization leads to richer value-of-information problems, usin...
We consider the multiple-response regression problem, where the response is subject to sparse gross errors, in the high-dimensional setup. We propose a tractable regularized M-est...
We introduce the graphlet decomposition of a weighted network, which encodes a notion of social information based on social structure. We develop a scalable algorithm, which combi...
We develop scalable algorithms for regular and non-negative matrix completion. In particular, we base the methods on trace-norm regularization that induces a low rank predicted ma...
We consider the minimization of a smooth loss with trace-norm regularization, which is a natural objective in multi-class and multitask learning. Even though the problem is convex...