7 search results - page 2 / 2 » A Unified Loss Function in Bayesian Framework for Support Ve... |
COLT
1999
Springer
13 years 9 months ago
1999
Springer
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Book
"Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning...