We present the first PAC bounds for learning parameters of Conditional Random Fields [12] with general structures over discrete and real-valued variables. Our bounds apply to com...
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The fi...
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...
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...