9 search results - page 1 / 2 » On the Complexity of Linear Prediction: Risk Bounds, Margin ... |
NIPS
2008
13 years 6 months ago
2008
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
NIPS
2001
13 years 6 months ago
2001
We give results about the learnability and required complexity of logical formulae to solve classification problems. These results are obtained by linking propositional logic with...
NAACL
2010
13 years 2 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...
NIPS
2001
13 years 6 months ago
2001
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
EMNLP
2011
12 years 4 months ago
2011
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...