Open Access
Translator Disclaimer
December 2014 Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
Zhaoran Wang, Han Liu, Tong Zhang
Ann. Statist. 42(6): 2164-2201 (December 2014). DOI: 10.1214/14-AOS1238

Abstract

We provide theoretical analysis of the statistical and computational properties of penalized $M$-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators fall in this category, including least squares regression with nonconvex regularization, generalized linear models with nonconvex regularization and sparse elliptical random design regression. For these problems, it is intractable to calculate the global solution due to the nonconvex formulation. In this paper, we propose an approximate regularization path-following method for solving a variety of learning problems with nonconvex objective functions. Under a unified analytic framework, we simultaneously provide explicit statistical and computational rates of convergence for any local solution attained by the algorithm. Computationally, our algorithm attains a global geometric rate of convergence for calculating the full regularization path, which is optimal among all first-order algorithms. Unlike most existing methods that only attain geometric rates of convergence for one single regularization parameter, our algorithm calculates the full regularization path with the same iteration complexity. In particular, we provide a refined iteration complexity bound to sharply characterize the performance of each stage along the regularization path. Statistically, we provide sharp sample complexity analysis for all the approximate local solutions along the regularization path. In particular, our analysis improves upon existing results by providing a more refined sample complexity bound as well as an exact support recovery result for the final estimator. These results show that the final estimator attains an oracle statistical property due to the usage of nonconvex penalty.

Citation

Download Citation

Zhaoran Wang. Han Liu. Tong Zhang. "Optimal computational and statistical rates of convergence for sparse nonconvex learning problems." Ann. Statist. 42 (6) 2164 - 2201, December 2014. https://doi.org/10.1214/14-AOS1238

Information

Published: December 2014
First available in Project Euclid: 20 October 2014

zbMATH: 1302.62066
MathSciNet: MR3269977
Digital Object Identifier: 10.1214/14-AOS1238

Subjects:
Primary: 62F30 , 90C26
Secondary: 62J12 , 90C52

Keywords: geometric computational rate , Nonconvex regularized $M$-estimation , optimal statistical rate , path-following method

Rights: Copyright © 2014 Institute of Mathematical Statistics

JOURNAL ARTICLE
38 PAGES


SHARE
Vol.42 • No. 6 • December 2014
Back to Top