HONES: A Fast and Tuning-free Homotopy Method For Online Newton Step

Yuting Ye, Lihua Lei, Cheng Ju
Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, PMLR 84:2008-2017, 2018.

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 (Hazan et al., 2006b), 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 this Paper

BibTeX
@InProceedings{pmlr-v84-ye18a, title = {HONES: A Fast and Tuning-free Homotopy Method For Online Newton Step}, author = {Ye, Yuting and Lei, Lihua and Ju, Cheng}, booktitle = {Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics}, pages = {2008--2017}, year = {2018}, editor = {Storkey, Amos and Perez-Cruz, Fernando}, volume = {84}, series = {Proceedings of Machine Learning Research}, month = {09--11 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v84/ye18a/ye18a.pdf}, url = {https://proceedings.mlr.press/v84/ye18a.html}, 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 (Hazan et al., 2006b), 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.} }
Endnote
%0 Conference Paper %T HONES: A Fast and Tuning-free Homotopy Method For Online Newton Step %A Yuting Ye %A Lihua Lei %A Cheng Ju %B Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2018 %E Amos Storkey %E Fernando Perez-Cruz %F pmlr-v84-ye18a %I PMLR %P 2008--2017 %U https://proceedings.mlr.press/v84/ye18a.html %V 84 %X 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 (Hazan et al., 2006b), 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.
APA
Ye, Y., Lei, L. & Ju, C.. (2018). HONES: A Fast and Tuning-free Homotopy Method For Online Newton Step. Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 84:2008-2017 Available from https://proceedings.mlr.press/v84/ye18a.html.

Related Material