5075 search results - page 10 / 1015 » Convergence |
AMC
2008
14 years 12 months ago
2008
Abstract: The nonlinear conjugate gradient method is widely used in unconstrained optimization. However, the line search is very difficult or expensive sometimes. In this paper, we...
TNN
1998
14 years 11 months ago
1998
—Oja’s principal subspace algorithm is a well-known and powerful technique for learning and tracking principal information in time series. A thorough investigation of the conve...
ORL
2008
14 years 11 months ago
2008
We discuss the almost-sure convergence of a broad class of sampling algorithms for multi-stage stochastic linear programs. We provide a convergence proof based on the finiteness o...
106
click to vote
FOCM
2008
14 years 10 months ago
2008
The Magnus series is an infinite series which arises in the study of linear ordinary differential equations. If the series converges, then the matrix exponential of the sum equals...
ICML
2003
IEEE
16 years 17 days 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 ...