We present multi-task structure learning for Gaussian graphical models. We discuss uniqueness and boundedness of the optimal solution of the maximization problem. A block coordina...
Fitting gaussian peaks to experimental data is important in many disciplines, including nuclear spectroscopy. Nonlinear least squares fitting methods have been in use for a long t...
Log-concavity is an important property in the context of optimization, Laplace approximation, and sampling; Bayesian methods based on Gaussian process priors have become quite pop...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
We present a probabilistic approach to learning a Gaussian Process classifier in the presence of unlabeled data. Our approach involves a "null category noise model" (NCN...