Accelerated Gradient Methods for Sparse Statistical Learning with Nonconvex Penalties
Preprint
- 28 November 2022
- preprint
- Published by Springer Nature in Research Square
Abstract
Nesterov’s accelerated gradient (AG) is a popular technique to optimize objective functions comprising two components: a convex loss and a penalty function. While AG methods perform well for convex penalties, such as the LASSO, convergence issues may arise when it is applied to nonconvex penalties, such as SCAD. A recent proposal generalizes Nesterov’s AG method to the nonconvex setting. The proposed algorithm requires specification of several hyperparameters for its practical application. Aside from some general conditions, there is no explicit rule for selecting the hyperparameters, and how different selection can affect convergence of the algorithm. In this article, we propose a hyperparameter setting based on the complexity upper bound to accelerate convergence, and consider the application of this nonconvex AG algorithm to high-dimensional linear and logistic sparse learning problems.We further establish the rate of convergence and present a simple and useful bound to characterize our proposed optimal damping sequence. Simulation studies show that convergencecan be made, on average, considerably faster than that of the conventional proximal gradientalgorithm. Our experiments also show that the proposed method generally outperforms the current state-of-the-art methods in terms of signal recovery.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Halting Time is Predictable for Large Models: A Universality Property and Average-Case AnalysisFoundations of Computational Mathematics, 2022
- Convergence rates for optimised adaptive importance samplersStatistics and Computing, 2021
- Non-concave penalization in linear mixed-effect models and regularized selection of fixed effectsAStA Advances in Statistical Analysis, 2017
- A modified local quadratic approximation algorithm for penalized optimization problemsComputational Statistics & Data Analysis, 2016
- Accelerated gradient methods for nonconvex nonlinear and stochastic programmingMathematical Programming, 2015
- A fast unified algorithm for solving group-lasso penalize learning problemsStatistics and Computing, 2014
- Gradient methods for minimizing composite functionsMathematical Programming, 2012
- Cyclic Seesaw Process for Optimization and IdentificationJournal of Optimization Theory and Applications, 2012
- An optimal method for stochastic composite optimizationMathematical Programming, 2011
- Introductory Lectures on Convex Optimization2004