101 search results - page 2 / 21 » Convergence of Gradient Dynamics with a Variable Learning Ra... |
JMLR
2010
13 years 1 months ago
2010
The problems of dimension reduction and inference of statistical dependence are addressed by the modeling framework of learning gradients. The models we propose hold for Euclidean...
COLT
2008
Springer
13 years 8 months ago
2008
Springer
Coordinate gradient learning is motivated by the problem of variable selection and determining variable covariation. In this paper we propose a novel unifying framework for coordi...
ICML
2004
IEEE
13 years 11 months ago
2004
IEEE
LASSO (Least Absolute Shrinkage and Selection Operator) is a useful tool to achieve the shrinkage and variable selection simultaneously. Since LASSO uses the L1 penalty, the optim...
ICML
2003
IEEE
14 years 7 months ago
2003
IEEE
In Reinforcement Learning (RL) there has been some experimental evidence that the residual gradient algorithm converges slower than the TD(0) algorithm. In this paper, we use the ...
ICML
2000
IEEE
14 years 7 months ago
2000
IEEE
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...