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...
We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
The objective of this work is classifying texture from a single image under unknown lighting conditions. The current and successful approach to this task is to treat it as a stati...
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
"How can we make sure our students learn what we want them to?" is the number one question in teaching. This paper is intended to provide the reader with: i) a general a...