BriefGPT.xyz
Jul, 2016
Frank-Wolfe算法在非凸目标中的收敛速率
Convergence Rate of Frank-Wolfe for Non-Convex Objectives
HTML
PDF
Simon Lacoste-Julien
TL;DR
该研究提供了一个简单的证明，表明Frank-Wolfe算法在具有Lipschitz连续梯度的非凸目标上，以O（1 / sqrt {t}）的速率获得静止点。
Abstract
We give a simple proof that the
frank-wolfe algorithm
obtains a
stationary point
at a rate of $O(1/\sqrt{t})$ on
non-convex objectives
wit
→