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

arXiv2101.01350MaRDI QIDQ6357589

Author name not available (Why is that?)

Publication date: 4 January 2021

Abstract: This paper primarily focuses on computing the Euclidean projection of a vector onto the $el{l}_p$ ball in which $pin(0,1)$. 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 $el{l}_1$-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 $O(1/sqrtk)$ convergence rate. Numerical experiments demonstrate the efficiency of our proposed algorithm.

Has companion code repository: https://github.com/optmizator/lp-ball-projection

This page was built for publication: Towards An Efficient Approach for the Nonconvex $\ell_p$ Ball Projection: Algorithm and Analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6357589)