Sciweavers

3381 search results - page 108 / 677
» LEO - DB2's LEarning Optimizer
Sort
View
ICML
2006
IEEE
14 years 11 months ago
Pareto optimal linear classification
We consider the problem of choosing a linear classifier that minimizes misclassification probabilities in two-class classification, which is a bi-criterion problem, involving a tr...
Seung-Jean Kim, Alessandro Magnani, Sikandar Samar...
ICML
2005
IEEE
14 years 11 months ago
Optimizing abstaining classifiers using ROC analysis
Classifiers that refrain from classification in certain cases can significantly reduce the misclassification cost. However, the parameters for such abstaining classifiers are ofte...
Tadeusz Pietraszek
IJCNN
2000
IEEE
14 years 2 months ago
On Derivation of MLP Backpropagation from the Kelley-Bryson Optimal-Control Gradient Formula and Its Application
The well-known backpropagation (BP) derivative computation process for multilayer perceptrons (MLP) learning can be viewed as a simplified version of the Kelley-Bryson gradient f...
Eiji Mizutani, Stuart E. Dreyfus, Kenichi Nishio
COLT
2006
Springer
14 years 1 months ago
Optimal Oracle Inequality for Aggregation of Classifiers Under Low Noise Condition
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 ...
Guillaume Lecué
COLT
2008
Springer
13 years 12 months ago
High-Probability Regret Bounds for Bandit Online Linear Optimization
We present a modification of the algorithm of Dani et al. [8] for the online linear optimization problem in the bandit setting, which with high probability has regret at most O ( ...
Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, S...