180 search results - page 15 / 36 » Improved bounds on the sample complexity of learning |
COLT
2005
Springer
14 years 1 months ago
2005
Springer
We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
NIPS
2008
13 years 9 months ago
2008
Empirical evidence shows that in favorable situations semi-supervised learning (SSL) algorithms can capitalize on the abundance of unlabeled training data to improve the performan...
JSAC
2006
13 years 7 months ago
2006
Abstract--Multiuser detection (MUD) for code-division multiple-access (CDMA) systems usually relies on some a priori channel estimates, which are obtained either blindly or by usin...
ICML
2003
IEEE
14 years 8 months ago
2003
IEEE
Recent theoretical results have shown that improved bounds on generalization error of classifiers can be obtained by explicitly taking the observed margin distribution of the trai...
ICML
2002
IEEE
14 years 8 months ago
2002
IEEE
Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each ...