66 search results - page 3 / 14 » Stochastic gradient descent on GPUs |
NIPS
2007
13 years 11 months ago
2007
Guided by the goal of obtaining an optimization algorithm that is both fast and yields good generalization, we study the descent direction maximizing the decrease in generalizatio...
SIAMJO
2000
13 years 9 months ago
2000
We consider the gradient method xt+1 = xt + t(st + wt), where st is a descent direction of a function f : n and wt is a deterministic or stochastic error. We assume that f is Lip...
JMLR
2006
13 years 9 months ago
2006
This paper presents an online support vector machine (SVM) that uses the stochastic meta-descent (SMD) algorithm to adapt its step size automatically. We formulate the online lear...
COLT
2010
Springer
13 years 7 months ago
2010
Springer
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstor...
ICML
2006
IEEE
14 years 10 months ago
2006
IEEE
We apply Stochastic Meta-Descent (SMD), a stochastic gradient optimization method with gain vector adaptation, to the training of Conditional Random Fields (CRFs). On several larg...