Off-the-grid prediction and testing for linear combination of translated features

TL;DR

This paper develops off-the-grid prediction bounds and goodness-of-fit tests for signals modeled as linear combinations of translated features with varying scale parameters, extending high-dimensional regression analysis.

Contribution

It introduces a non-linear extension of high-dimensional regression with variable scale features, providing new prediction bounds and minimax separation rates for signal detection.

Findings

Prediction bounds are improved by increasing the minimal distance between features.

A goodness-of-fit test with non-asymptotic risk bounds is proposed.

Upper bounds on the energy needed for successful signal detection are established.

Abstract

We consider a model where a signal (discrete or continuous) is observed with an additive Gaussian noise process. The signal is issued from a linear combination of a finite but increasing number of translated features. The features are continuously parameterized by their location and depend on some scale parameter. First, we extend previous prediction results for off-the-grid estimators by taking into account here that the scale parameter may vary. The prediction bounds are analogous, but we improve the minimal distance between two consecutive features locations in order to achieve these bounds. Next, we propose a goodness-of-fit test for the model and give non-asymptotic upper bounds of the testing risk and of the minimax separation rate between two distinguishable signals. In particular, our test encompasses the signal detection framework. We deduce upper bounds on the minimal energy,expressed as the $\ell_2$-norm of the linear coefficients, to successfully detect a signal in presence of noise. The general model considered in this paper is a non-linear extension of the classical high-dimensional regression model. It turns out that,in this framework, our upper bound on the minimax separation rate matches (up to a logarithmic factor) the lower bound on the minimax separation rate for signal detection in the high-dimensional linear model associated to a fixed dictionary of features. We also propose a procedure to test whether the features of the observed signal belong to a given finite collection under the assumption that the linear coefficients may vary, but have prescribed signs under the null hypothesis. A non-asymptotic upper bound on the testing risk is given.We illustrate our results on the spikes deconvolution model with Gaussian features on the real line and with the Dirichlet kernel, frequently used in the compressed sensing literature, on the torus.