论在线镜像下降的普适性
机器学习
2011-07-21 v1
摘要
我们证明，对于一大类凸在线学习问题，镜像下降总能实现（近乎）最优的遗憾保证。
引用
@article{arxiv.1107.4080,
title = {On the Universality of Online Mirror Descent},
author = {Nathan Srebro and Karthik Sridharan and Ambuj Tewari},
journal= {arXiv preprint arXiv:1107.4080},
year = {2011}
}