Off-the-grid learning of sparse mixtures from a continuous dictionary

06/29/2022
by   Cristina Butucea, et al.
14

We consider a general non-linear model where the signal is a finite mixture of an unknown, possibly increasing, number of features issued from a continuous dictionary parameterized by a real nonlinear parameter. The signal is observed with Gaussian (possibly correlated) noise in either a continuous or a discrete setup. We propose an off-the-grid optimization method, that is, a method which does not use any discretization scheme on the parameter space, to estimate both the non-linear parameters of the features and the linear parameters of the mixture. We use recent results on the geometry of off-the-grid methods to give minimal separation on the true underlying non-linear parameters such that interpolating certificate functions can be constructed. Using also tail bounds for suprema of Gaussian processes we bound the prediction error with high probability. Assuming that the certificate functions can be constructed, our prediction error bound is up to log –factors similar to the rates attained by the Lasso predictor in the linear regression model. We also establish convergence rates that quantify with high probability the quality of estimation for both the linear and the non-linear parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/27/2022

Simultaneous off-the-grid learning of mixtures issued from a continuous dictionary

In this paper we observe a set, possibly a continuum, of signals corrupt...
research
12/02/2022

Off-the-grid prediction and testing for mixtures of translated features

We consider a model where a signal (discrete or continuous) is observed ...
research
04/04/2021

D-optimal designs for the Mitscherlich non-linear regression function

Mitscherlich's function is a well-known three-parameter non-linear regre...
research
04/30/2013

Dictionary LASSO: Guaranteed Sparse Recovery under Linear Transformation

We consider the following signal recovery problem: given a measurement m...
research
02/12/2020

Sparse Recovery With Non-Linear Fourier Features

Random non-linear Fourier features have recently shown remarkable perfor...
research
05/12/2022

Probabilistic Estimation of Chirp Instantaneous Frequency Using Gaussian Processes

We present a probabilistic approach for estimating chirp signal and its ...
research
11/14/2019

Sparse Density Estimation with Measurement Errors

This paper aims to build an estimate of an unknown density of the data w...

Please sign up or login with your details

Forgot password? Click here to reset