Most existing semi-supervised learning methods are based on the smoothness assumption that data points in the same high density region should have the same label. This assumption, ...
Recently there has been significant interest in supervised learning algorithms that combine labeled and unlabeled data for text learning tasks. The co-training setting [1] applie...
Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structur...
Abstract— A distributed online learning framework for support vector machines (SVMs) is presented and analyzed. First, the generic binary classification problem is decomposed in...
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...