Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning
Abstract
We propose a stochastic variance reduced optimization algorithm for solving a class of large-scale nonconvex optimization problems with cardinality constraints, and provide sufficient conditions under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. Numerical experiments demonstrate the efficiency of our method in terms of both parameter estimation and computational performance.
Cite
Text
Li et al. "Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning." International Conference on Machine Learning, 2016.Markdown
[Li et al. "Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/li2016icml-stochastic/)BibTeX
@inproceedings{li2016icml-stochastic,
title = {{Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning}},
author = {Li, Xingguo and Zhao, Tuo and Arora, Raman and Liu, Han and Haupt, Jarvis},
booktitle = {International Conference on Machine Learning},
year = {2016},
pages = {917-925},
volume = {48},
url = {https://mlanthology.org/icml/2016/li2016icml-stochastic/}
}