Sciweavers

SIAMJO
2000
67views more  SIAMJO 2000»
13 years 4 months ago
Gradient Convergence in Gradient methods with Errors
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...
Dimitri P. Bertsekas, John N. Tsitsiklis