21 search results - page 2 / 5 » Local Complexities for Empirical Risk Minimization |
IJCNN
2007
IEEE
14 years 1 months ago
2007
IEEE
— To obtain accurate modeling results, it is of primal importance to find optimal values for the hyperparameters in the Support Vector Regression (SVR) model. In general, we sea...
ACL
2006
13 years 8 months ago
2006
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
LACL
2005
Springer
14 years 26 days ago
2005
Springer
Locality Conditions (LCs) on (unbounded) dependencies have played a major role in the development of generative syntax ever since the seminal work by Ross [22]. Descriptively, they...
COLT
2000
Springer
13 years 11 months ago
2000
Springer
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...
JMLR
2010
13 years 5 months ago
2010
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by ge...