Sciweavers

Share
2 search results - page 1 / 1
» Scalable training of L1-regularized log-linear models
Sort
View
ICML
2007
IEEE
10 years 10 months ago
Scalable training of L1-regularized log-linear models
The l-bfgs limited-memory quasi-Newton method is the algorithm of choice for optimizing the parameters of large-scale log-linear models with L2 regularization, but it cannot be us...
Galen Andrew, Jianfeng Gao
NIPS
2007
9 years 11 months ago
Discriminative Log-Linear Grammars with Latent Variables
We demonstrate that log-linear grammars with latent variables can be practically trained using discriminative methods. Central to ef´Čücient discriminative training is a hierarchi...
Slav Petrov, Dan Klein
books