@inproceedings{5ecef4374c8a4688b0d66fd860b3a9ec,
title = "Constrained Stochastic Gradient Descent: The Good Practice",
abstract = "Stochastic Gradient Descent (SGD) is the method of choice for large scale problems, most notably in deep learning. Recent studies target improving convergence and speed of the SGD algorithm. In this paper, we equip the SGD algorithm and its advanced versions with an intriguing feature, namely handling constrained problems. Constraints such as orthogonality are pervasive in learning theory. Nevertheless and to some extent surprising, constrained SGD algorithms are rarely studied. Our proposal makes use of Riemannian geometry and accelerated optimization techniques to deliver efficient and constrained-aware SGD methods.We will assess and contrast our proposed approaches in a wide range of problems including incremental dimensionality reduction, karcher mean and deep metric learning.",
author = "Roy, {Soumava Kumar} and Mehrtash Harandi",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2017 ; Conference date: 29-11-2017 Through 01-12-2017",
year = "2017",
month = dec,
day = "19",
doi = "10.1109/DICTA.2017.8227420",
language = "English",
series = "DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--8",
editor = "Yi Guo and Manzur Murshed and Zhiyong Wang and Feng, {David Dagan} and Hongdong Li and Cai, {Weidong Tom} and Junbin Gao",
booktitle = "DICTA 2017 - 2017 International Conference on Digital Image Computing",
address = "United States",
}