Sciweavers

69 search results - page 3 / 14
» Random Sampling of Labeled Tournaments
Sort
View
NIPS
2004
13 years 7 months ago
Worst-Case Analysis of Selective Sampling for Linear-Threshold Algorithms
We provide a worst-case analysis of selective sampling algorithms for learning linear threshold functions. The algorithms considered in this paper are Perceptron-like algorithms, ...
Nicolò Cesa-Bianchi, Claudio Gentile, Luca ...
JMLR
2006
99views more  JMLR 2006»
13 years 5 months ago
Worst-Case Analysis of Selective Sampling for Linear Classification
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...
Nicolò Cesa-Bianchi, Claudio Gentile, Luca ...
ICML
2006
IEEE
14 years 6 months ago
An analysis of graph cut size for transductive learning
I consider the setting of transductive learning of vertex labels in graphs, in which a graph with n vertices is sampled according to some unknown distribution; there is a true lab...
Steve Hanneke
AAAI
2000
13 years 7 months ago
Selective Sampling with Redundant Views
Selective sampling, a form of active learning, reduces the cost of labeling training data by asking only for the labels of the most informative unlabeled examples. We introduce a ...
Ion Muslea, Steven Minton, Craig A. Knoblock
FOIKS
2008
Springer
14 years 2 months ago
Cost-minimising strategies for data labelling : optimal stopping and active learning
Supervised learning deals with the inference of a distribution over an output or label space $\CY$ conditioned on points in an observation space $\CX$, given a training dataset $D$...
Christos Dimitrakakis, Christian Savu-Krohn