solidot新版网站常见问题,请点击这里查看。
消息
本文已被查看15651次
A single potential governing convergence of conjugate gradient, accelerated gradient and geometric descent. (arXiv:1712.09498v1 [math.OC])
来源于:arXiv
Nesterov's accelerated gradient (AG) method for minimizing a smooth strongly
convex function $f$ is known to reduce $f({\bf x}_k)-f({\bf x}^*)$ by a factor
of $\epsilon\in(0,1)$ after $k=O(\sqrt{L/\ell}\log(1/\epsilon))$ iterations,
where $\ell,L$ are the two parameters of smooth strong convexity. Furthermore,
it is known that this is the best possible complexity in the function-gradient
oracle model of computation. Modulo a line search, the geometric descent (GD)
method of Bubeck, Lee and Singh has the same bound for this class of functions.
The method of linear conjugate gradients (CG) also satisfies the same
complexity bound in the special case of strongly convex quadratic functions,
but in this special case it can be faster than the AG and GD methods.
Despite similarities in the algorithms and their asymptotic convergence
rates, the conventional analysis of the running time of CG is mostly disjoint
from that of AG and GD. The analyses of the AG and GD methods are also rather
distin 查看全文>>