Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction
Machine Learning
2017-12-27 v5 Optimization and Control
Machine Learning
Abstract
We propose a stochastic variance reduced optimization algorithm for solving sparse learning problems with cardinality constraints. Sufficient conditions are provided, under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. We further extend the proposed algorithm to an asynchronous parallel variant with a near linear speedup. Numerical experiments demonstrate the efficiency of our algorithm in terms of both parameter estimation and computational performance.
Cite
@article{arxiv.1605.02711,
title = {Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction},
author = {Xingguo Li and Raman Arora and Han Liu and Jarvis Haupt and Tuo Zhao},
journal= {arXiv preprint arXiv:1605.02711},
year = {2017}
}