39 search results - page 5 / 8 » colt 2006 |
101
click to vote
COLT
2006
Springer
15 years 7 months ago
2006
Springer
We consider the problem of optimality, in a minimax sense, and adaptivity to the margin and to regularity in binary classification. We prove an oracle inequality, under the margin ...
128
Voted
COLT
2006
Springer
15 years 7 months ago
2006
Springer
Generative algorithms for learning classifiers use training data to separately estimate a probability model for each class. New items are classified by comparing their probabiliti...
155
click to vote
COLT
2006
Springer
15 years 7 months ago
2006
Springer
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
123
click to vote
COLT
2006
Springer
15 years 7 months ago
2006
Springer
Abstract. We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolut...
144
Voted
COLT
2006
Springer
15 years 7 months ago
2006
Springer
Abstract. We develop a new error bound for transductive learning algorithms. The slack term in the new bound is a function of a relaxed notion of transductive stability, which meas...