324 search results - page 11 / 65 » Bounds for Functions of Dependent Risks |
110
click to vote
NIPS
2004
15 years 3 months ago
2004
We study a method of optimal data-driven aggregation of classifiers in a convex combination and establish tight upper bounds on its excess risk with respect to a convex loss funct...
122
click to vote
NAACL
2010
14 years 11 months ago
2010
We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduc...
122
click to vote
COLT
2006
Springer
15 years 5 months ago
2006
Springer
We propose a sequential randomized algorithm, which at each step concentrates on functions having both low risk and low variance with respect to the previous step prediction functi...
117
click to vote
HPDC
2007
IEEE
15 years 8 months ago
2007
IEEE
We study stochastic models to mitigate the risk of poor Quality-of-Service (QoS) in computational markets. Consumers who purchase services expect both price and performance guaran...
117
Voted
JMLR
2008
15 years 1 months ago
2008
A method is introduced to learn and represent similarity with linear operators in kernel induced Hilbert spaces. Transferring error bounds for vector valued large-margin classifie...