Local Geometry of Nonconvex Spike Deconvolution from Low-Pass Measurements

08/22/2022
by   Maxime Ferreira Da Costa, et al.
0

Spike deconvolution is the problem of recovering the point sources from their convolution with a known point spread function, which plays a fundamental role in many sensing and imaging applications. In this paper, we investigate the local geometry of recovering the parameters of point sourcesx2014including both amplitudes and locationsx2014by minimizing a natural nonconvex least-squares loss function measuring the observation residuals. We propose preconditioned variants of gradient descent (GD), where the search direction is scaled via some carefully designed preconditioning matrices. We begin with a simple fixed preconditioner design, which adjusts the learning rates of the locations at a different scale from those of the amplitudes, and show it achieves a linear rate of convergencex2014in terms of entrywise errorsx2014when initialized close to the ground truth, as long as the separation between the true spikes is sufficiently large. However, the convergence rate slows down significantly when the dynamic range of the source amplitudes is large. To bridge this issue, we introduce an adaptive preconditioner design, which compensates for the learning rates of different sources in an iteration-varying manner based on the current estimate. The adaptive design provably leads to an accelerated convergence rate that is independent of the dynamic range, highlighting the benefit of adaptive preconditioning in nonconvex spike deconvolution. Numerical experiments are provided to corroborate the theoretical findings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/03/2019

On the Stable Resolution Limit of Total Variation Regularization for Spike Deconvolution

The stability of spike deconvolution, which aims at recovering point sou...
research
06/07/2022

Preconditioned Gradient Descent for Overparameterized Nonconvex Burer–Monteiro Factorization with Global Optimality Certification

We consider using gradient descent to minimize the nonconvex function f(...
research
01/07/2019

On the Global Geometry of Sphere-Constrained Sparse Blind Deconvolution

Blind deconvolution is the problem of recovering a convolutional kernel ...
research
09/18/2021

Coordinate Descent for MCP/SCAD Penalized Least Squares Converges Linearly

Recovering sparse signals from observed data is an important topic in si...
research
01/02/2019

Geometry and Symmetry in Short-and-Sparse Deconvolution

We study the Short-and-Sparse (SaS) deconvolution problem of recovering ...
research
09/18/2018

Nonconvex Demixing From Bilinear Measurements

We consider the problem of demixing a sequence of source signals from th...
research
03/30/2020

A Sampling Theorem for Deconvolution in Two Dimensions

This work studies the problem of estimating a two-dimensional superposit...

Please sign up or login with your details

Forgot password? Click here to reset