HONES: A Fast and Tuning-Free Homotopy Method for Online Newton Step
Abstract
In this article, we develop and analyze a homotopy continuation method, referred to as HONES , for solving the sequential generalized projections in Online Newton Step, as well as the generalized problem known as sequential standard quadratic programming. HONES is fast, tuning-free, error-free (up to machine error) and adaptive to the solution sparsity. This is confirmed by both careful theoretical analysis and extensive experiments on both synthetic and real data.
Cite
Text
Ye et al. "HONES: A Fast and Tuning-Free Homotopy Method for Online Newton Step." International Conference on Artificial Intelligence and Statistics, 2018.Markdown
[Ye et al. "HONES: A Fast and Tuning-Free Homotopy Method for Online Newton Step." International Conference on Artificial Intelligence and Statistics, 2018.](https://mlanthology.org/aistats/2018/ye2018aistats-hones/)BibTeX
@inproceedings{ye2018aistats-hones,
title = {{HONES: A Fast and Tuning-Free Homotopy Method for Online Newton Step}},
author = {Ye, Yuting and Lei, Lihua and Ju, Cheng},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2018},
pages = {2008-2017},
url = {https://mlanthology.org/aistats/2018/ye2018aistats-hones/}
}