Convergence and Rate Analysis of Neural Networks for Sparse Approximation
arXiv:1107.5988 · doi:10.1109/TNNLS.2012.2202400
Abstract
We present an analysis of the Locally Competitive Algorithm (LCA), a Hopfield-style neural network that efficiently solves sparse approximation problems (e.g., approximating a vector from a dictionary using just a few non-zero coefficients). This class of problems plays a significant role in both theories of neural coding and applications in signal processing. However, the LCA lacks analysis of its convergence properties and previous results on neural networks for nonsmooth optimization do not apply to the specifics of the LCA architecture. We show that the LCA has desirable convergence properties, such as stability and global convergence to the optimum of the objective function when it is unique. Under some mild conditions, the support of the solution is also proven to be reached in finite time. Furthermore, some restrictions on the problem specifics allow us to characterize the convergence rate of the system by showing that the LCA converges exponentially fast with an analytically bounded convergence rate. We support our analysis with several illustrative simulations.
12 pages, 8 figures The statement and proof of Theorem 3 have been corrected in this version
References in corpus (1)
Cited by in corpus (11)
- Convergence Speed of a Dynamical System for Sparse Recovery
- Discrete and Continuous-time Soft-Thresholding with Dynamic Inputs
- Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results
- When can dictionary learning uniquely recover sparse data from subsamples?
- Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
- Analog Sparse Approximation with Applications to Compressed Sensing
- Convergence of LCA Flows to (C)LASSO Solutions
- Robust MIMO Radar Target Localization based on Lagrange Programming Neural Network
- Short Term Memory Capacity in Networks via the Restricted Isometry Property
- Robust Real-time Ellipse Fitting Based on Lagrange Programming Neural Network and Locally Competitive Algorithm
- Fast L1-Minimization Algorithm for Sparse Approximation Based on an Improved LPNN-LCA framework