CAPPA: Continuous-time Accelerated Proximal Point Algorithm for Sparse Recovery
Abstract
This paper develops a novel Continuous-time Accelerated Proximal Point Algorithm (CAPPA) for -minimization problems with provable fixed-time convergence guarantees. The problem of -minimization appears in several contexts, such as sparse recovery (SR) in Compressed Sensing (CS) theory, and sparse linear and logistic regressions in machine learning to name a few. Most existing algorithms for solving -minimization problems are discrete-time, inefficient and require exhaustive computer-guided iterations. CAPPA alleviates this problem on two fronts: (a) it encompasses a continuous-time algorithm that can be implemented using analog circuits; (b) it betters LCA and finite-time LCA (recently developed continuous-time dynamical systems for solving SR problems) by exhibiting provable fixed-time convergence to optimal solution. Consequently, CAPPA is better suited for fast and efficient handling of SR problems. Simulation studies are presented that corroborate computational advantages of CAPPA.
Cite
@article{arxiv.2006.02537,
title = {CAPPA: Continuous-time Accelerated Proximal Point Algorithm for Sparse Recovery},
author = {Kunal Garg and Mayank Baranwal},
journal= {arXiv preprint arXiv:2006.02537},
year = {2020}
}
Comments
6 pages, 5 figures