58 search results - page 2 / 12 » Approximation accuracy, gradient methods, and error bound fo... |
ICDM
2009
IEEE
13 years 12 months ago
2009
IEEE
—Many real world learning problems can be recast as multi-task learning problems which utilize correlations among different tasks to obtain better generalization performance than...
NIPS
2008
13 years 6 months ago
2008
Large-margin structured estimation methods minimize a convex upper bound of loss functions. While they allow for efficient optimization algorithms, these convex formulations are n...
CORR
2011
Springer
12 years 11 months ago
2011
Springer
We analyze a class of estimators based on a convex relaxation for solving highdimensional matrix decomposition problems. The observations are the noisy realizations of the sum of ...
ICCV
2005
IEEE
14 years 7 months ago
2005
IEEE
Geometric reconstruction problems in computer vision are often solved by minimizing a cost function that combines the reprojection errors in the 2D images. In this paper, we show t...
JMLR
2008
13 years 5 months ago
2008
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...