Optimal computational and statistical rates of convergence for sparse nonconvex learning problems

Zhaoran Wang, Han Liu, Tong Zhang

Research output: Contribution to journalArticlepeer-review

73 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)2164-2201
Number of pages38
JournalAnnals of Statistics
Volume42
Issue number6
DOIs
StatePublished - Dec 1 2014

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Keywords

  • Geometric computational rate
  • Nonconvex regularized M-estimation
  • Optimal statistical rate
  • Path-following method

Fingerprint Dive into the research topics of 'Optimal computational and statistical rates of convergence for sparse nonconvex learning problems'. Together they form a unique fingerprint.

Cite this