Variants of RMSProp and AdaGrad with Logarithmic Regret Bounds
Abstract
Adaptive gradient methods have become recently very popular, in particular as they have been shown to be useful in the training of deep neural networks. In this paper we have analyzed RMSProp, originally proposed for the training of deep neural networks, in the context of online convex optimization and show $\sqrt{T}$-type regret bounds. Moreover, we propose two variants SC-Adagrad and SC-RMSProp for which we show logarithmic regret bounds for strongly convex functions. Finally, we demonstrate in the experiments that these new variants outperform other adaptive gradient techniques or stochastic gradient descent in the optimization of strongly convex functions as well as in training of deep neural networks.
Cite
Text
Mukkamala and Hein. "Variants of RMSProp and AdaGrad with Logarithmic Regret Bounds." International Conference on Machine Learning, 2017.Markdown
[Mukkamala and Hein. "Variants of RMSProp and AdaGrad with Logarithmic Regret Bounds." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/mukkamala2017icml-variants/)BibTeX
@inproceedings{mukkamala2017icml-variants,
title = {{Variants of RMSProp and AdaGrad with Logarithmic Regret Bounds}},
author = {Mukkamala, Mahesh Chandra and Hein, Matthias},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {2545-2553},
volume = {70},
url = {https://mlanthology.org/icml/2017/mukkamala2017icml-variants/}
}