683 search results - page 18 / 137 » Generalization Bounds for Learning Kernels |
COLT
2001
Springer
13 years 12 months ago
2001
Springer
We consider geometric conditions on a labeled data set which guarantee that boosting algorithms work well when linear classifiers are used as weak learners. We start by providing ...
ALT
2010
Springer
13 years 4 months ago
2010
Springer
This paper provides a probabilistic derivation of an identity connecting the square loss of ridge regression in on-line mode with the loss of a retrospectively best regressor. Some...
ML
2007
ACM
13 years 6 months ago
2007
ACM
In many learning problems prior knowledge about pattern variations can be formalized and beneficially incorporated into the analysis system. The corresponding notion of invarianc...
SODA
2012
ACM
11 years 9 months ago
2012
ACM
Kernelization algorithms are polynomial-time reductions from a problem to itself that guarantee their output to have a size not exceeding some bound. For example, d-Set Matching f...
JAIR
2002
13 years 7 months ago
2002
We develop, analyze, and evaluate a novel, supervised, specific-to-general learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions fr...