Positive Competitive Networks for Sparse Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Centorrino, Veronica, Gokhale, Anand, Davydov, Alexander, Russo, Giovanni, Bullo, Francesco
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910378322034688
author Centorrino, Veronica
Gokhale, Anand
Davydov, Alexander
Russo, Giovanni
Bullo, Francesco
author_facet Centorrino, Veronica
Gokhale, Anand
Davydov, Alexander
Russo, Giovanni
Bullo, Francesco
contents We propose and analyze a continuous-time firing-rate neural network, the positive firing-rate competitive network (\pfcn), to tackle sparse reconstruction problems with non-negativity constraints. These problems, which involve approximating a given input stimulus from a dictionary using a set of sparse (active) neurons, play a key role in a wide range of domains, including for example neuroscience, signal processing, and machine learning. First, by leveraging the theory of proximal operators, we relate the equilibria of a family of continuous-time firing-rate neural networks to the optimal solutions of sparse reconstruction problems. Then, we prove that the \pfcn is a positive system and give rigorous conditions for the convergence to the equilibrium. Specifically, we show that the convergence: (i) only depends on a property of the dictionary; (ii) is linear-exponential, in the sense that initially the convergence rate is at worst linear and then, after a transient, it becomes exponential. We also prove a number of technical results to assess the contractivity properties of the neural dynamics of interest. Our analysis leverages contraction theory to characterize the behavior of a family of firing-rate competitive networks for sparse reconstruction with and without non-negativity constraints. Finally, we validate the effectiveness of our approach via a numerical example.
format Preprint
id arxiv_https___arxiv_org_abs_2311_03821
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Positive Competitive Networks for Sparse Reconstruction
Centorrino, Veronica
Gokhale, Anand
Davydov, Alexander
Russo, Giovanni
Bullo, Francesco
Neurons and Cognition
Systems and Control
Optimization and Control
We propose and analyze a continuous-time firing-rate neural network, the positive firing-rate competitive network (\pfcn), to tackle sparse reconstruction problems with non-negativity constraints. These problems, which involve approximating a given input stimulus from a dictionary using a set of sparse (active) neurons, play a key role in a wide range of domains, including for example neuroscience, signal processing, and machine learning. First, by leveraging the theory of proximal operators, we relate the equilibria of a family of continuous-time firing-rate neural networks to the optimal solutions of sparse reconstruction problems. Then, we prove that the \pfcn is a positive system and give rigorous conditions for the convergence to the equilibrium. Specifically, we show that the convergence: (i) only depends on a property of the dictionary; (ii) is linear-exponential, in the sense that initially the convergence rate is at worst linear and then, after a transient, it becomes exponential. We also prove a number of technical results to assess the contractivity properties of the neural dynamics of interest. Our analysis leverages contraction theory to characterize the behavior of a family of firing-rate competitive networks for sparse reconstruction with and without non-negativity constraints. Finally, we validate the effectiveness of our approach via a numerical example.
title Positive Competitive Networks for Sparse Reconstruction
topic Neurons and Cognition
Systems and Control
Optimization and Control
url https://arxiv.org/abs/2311.03821