BriefGPT.xyz
Jan, 2013
一种线性收敛的条件梯度算法及其在在线和随机优化中的应用
A Polynomial Time Conditional Gradient Algorithm with Applications to Online and Stochastic Optimization
HTML
PDF
Dan Garber, Elad Hazan
TL;DR
本研究介绍了一种基于条件梯度算法的优化模型,可用于求解线性优化问题和非线性凸优化问题,并给出了一种基于此算法的在线凸优化算法,具有线性收敛速度和最优的遗憾保证。
Abstract
The conditional gradient method is a long-studied first-order optimization method for smooth
convex optimization
. Its main appeal is the low computational complexity: the conditional gradient method requires only a single
→