Towards An Efficient Approach for the Nonconvex $\ell_p$ Ball Projection: Algorithm and Analysis

TL;DR

This paper introduces an efficient algorithm for projecting vectors onto the nonconvex _p ball with p in (0,1), crucial for sparse solutions in machine learning, by solving a sequence of reweighted _1 projections.

Contribution

It develops the first practical, convergent algorithm for _p ball projection, addressing a key computational challenge in sparse optimization.

Findings

Algorithm converges uniquely under mild conditions.

Achieves a worst-case (1/ oot{k}) convergence rate.

Numerical experiments confirm efficiency and practicality.

Abstract

This paper primarily focuses on computing the Euclidean projection of a vector onto the $\ell_{p}$ ball in which $p\in(0,1)$. Such a problem emerges as the core building block in statistical machine learning and signal processing tasks because of its ability to promote the sparsity of the desired solution. However, efficient numerical algorithms for finding the projections are still not available, particularly in large-scale optimization. To meet this challenge, we first derive the first-order necessary optimality conditions of this problem. Based on this characterization, we develop a novel numerical approach for computing the stationary point by solving a sequence of projections onto the reweighted $\ell_{1}$-balls. This method is practically simple to implement and computationally efficient. Moreover, the proposed algorithm is shown to converge uniquely under mild conditions and has a worst-case $O(1/\sqrt{k})$ convergence rate. Numerical experiments demonstrate the efficiency of our proposed algorithm.