191
click to vote
JMLR
2012
13 years 9 months ago
2012
We study sparse principal components analysis in the high-dimensional setting, where p (the number of variables) can be much larger than n (the number of observations). We prove o...
217
click to vote
JMLR
2012
13 years 9 months ago
2012
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
204
click to vote
JMLR
2012
13 years 9 months ago
2012
We study the problem of learning a group of principal tasks using a group of auxiliary tasks, unrelated to the principal ones. In many applications, joint learning of unrelated ta...
221
click to vote
JMLR
2012
13 years 9 months ago
2012
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
212
click to vote
JMLR
2012
13 years 9 months ago
2012
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by specifically training on this task, evaluating m...