148 search results - page 12 / 30 » Bounds for Linear Multi-Task Learning |
EWRL
2008
13 years 9 months ago
2008
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
ICML
2008
IEEE
14 years 8 months ago
2008
IEEE
After a classifier is trained using a machine learning algorithm and put to use in a real world system, it often faces noise which did not appear in the training data. Particularl...
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
We introduce a new algorithm for binary classification in the selective sampling protocol. Our algorithm uses Regularized Least Squares (RLS) as base classifier, and for this reas...
JMLR
2006
13 years 7 months ago
2006
A selective sampling algorithm is a learning algorithm for classification that, based on the past observed data, decides whether to ask the label of each new instance to be classi...
SIAMJO
2010
13 years 2 months ago
2010
We study the problem of minimizing the expected loss of a linear predictor while constraining its sparsity, i.e., bounding the number of features used by the predictor. While the r...