ICML 2017poster32 citations
Follow the Moving Leader in Deep Learning
Abstract
Deep networks are highly nonlinear and difficult to optimize. During training, the parameter iterate may move from one local basin to another, or the data distribution may even change. Inspired by the close connection between stochastic optimization and online learning, we propose a variant of the
BibTeX
@InProceedings{pmlr-v70-zheng17a,
title = {Follow the Moving Leader in Deep Learning},
author = {Shuai Zheng and James T. Kwok},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {4110--4119},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/zheng17a/zheng17a.pdf},
url = {https://proceedings.mlr.press/v70/zheng17a.html},
abstract = {Deep networks are highly nonlinear and difficult to optimize. During training, the parameter iterate may move from one local basin to another, or the data distribution may even change. Inspired by the close connection between stochastic optimization and online learning, we propose a variant of the